{ "description": "Detects objects, explicit content, and scene changes in videos. It also specifies the region for annotation and transcribes speech to text. Supports both asynchronous API and streaming API.", "discoveryVersion": "v1", "id": "videointelligence:v1p1beta1", "protocol": "rest", "canonicalName": "Cloud Video Intelligence", "rootUrl": "https://videointelligence.googleapis.com/", "auth": { "oauth2": { "scopes": { "https://www.googleapis.com/auth/cloud-platform": { "description": "See, edit, configure, and delete your Google Cloud data and see the email address for your Google Account." } } } }, "icons": { "x32": "http://www.google.com/images/icons/product/search-32.gif", "x16": "http://www.google.com/images/icons/product/search-16.gif" }, "resources": { "videos": { "methods": { "annotate": { "parameters": {}, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "id": "videointelligence.videos.annotate", "flatPath": "v1p1beta1/videos:annotate", "path": "v1p1beta1/videos:annotate", "response": { "$ref": "GoogleLongrunning_Operation" }, "description": "Performs asynchronous video annotation. Progress and results can be retrieved through the `google.longrunning.Operations` interface. `Operation.metadata` contains `AnnotateVideoProgress` (progress). `Operation.response` contains `AnnotateVideoResponse` (results).", "httpMethod": "POST", "request": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoRequest" }, "parameterOrder": [] } } } }, "fullyEncodeReservedExpansion": true, "revision": "20260428", "parameters": { "prettyPrint": { "type": "boolean", "description": "Returns response with indentations and line breaks.", "default": "true", "location": "query" }, "callback": { "type": "string", "description": "JSONP", "location": "query" }, "key": { "description": "API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.", "location": "query", "type": "string" }, "quotaUser": { "description": "Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.", "location": "query", "type": "string" }, "fields": { "description": "Selector specifying which fields to include in a partial response.", "location": "query", "type": "string" }, "$.xgafv": { "enumDescriptions": [ "v1 error format", "v2 error format" ], "description": "V1 error format.", "enum": [ "1", "2" ], "location": "query", "type": "string" }, "upload_protocol": { "type": "string", "description": "Upload protocol for media (e.g. \"raw\", \"multipart\").", "location": "query" }, "access_token": { "type": "string", "description": "OAuth access token.", "location": "query" }, "alt": { "enumDescriptions": [ "Responses with Content-Type of application/json", "Media download with context-dependent Content-Type", "Responses with Content-Type of application/x-protobuf" ], "description": "Data format for response.", "default": "json", "enum": [ "json", "media", "proto" ], "location": "query", "type": "string" }, "oauth_token": { "description": "OAuth 2.0 token for the current user.", "location": "query", "type": "string" }, "uploadType": { "type": "string", "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").", "location": "query" } }, "title": "Cloud Video Intelligence API", "mtlsRootUrl": "https://videointelligence.mtls.googleapis.com/", "kind": "discovery#restDescription", "schemas": { "GoogleCloudVideointelligenceV1p1beta1_SpeechContext": { "id": "GoogleCloudVideointelligenceV1p1beta1_SpeechContext", "type": "object", "properties": { "phrases": { "type": "array", "description": "Optional. A list of strings containing words and phrases \"hints\" so that the speech recognition is more likely to recognize them. This can be used to improve the accuracy for specific words and phrases, for example, if specific commands are typically spoken by the user. This can also be used to add additional words to the vocabulary of the recognizer. See [usage limits](https://cloud.google.com/speech/limits#content).", "items": { "type": "string" } } }, "description": "Provides \"hints\" to the speech recognizer to favor specific words and phrases in the results." }, "GoogleCloudVideointelligenceV1beta2_TextFrame": { "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.", "type": "object", "properties": { "rotatedBoundingBox": { "description": "Bounding polygon of the detected text for this frame.", "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingPoly" }, "timeOffset": { "description": "Timestamp of this frame.", "format": "google-duration", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1beta2_TextFrame" }, "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox": { "type": "object", "properties": { "left": { "description": "Left X coordinate.", "format": "float", "type": "number" }, "bottom": { "description": "Bottom Y coordinate.", "format": "float", "type": "number" }, "top": { "description": "Top Y coordinate.", "format": "float", "type": "number" }, "right": { "type": "number", "description": "Right X coordinate.", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox", "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1]." }, "GoogleCloudVideointelligenceV1beta2_FaceFrame": { "description": "Deprecated. No effect.", "deprecated": true, "type": "object", "properties": { "normalizedBoundingBoxes": { "type": "array", "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox" } }, "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "format": "google-duration", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1beta2_FaceFrame" }, "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingAnnotation": { "type": "object", "properties": { "trackId": { "type": "string", "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time.", "format": "int64" }, "segment": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment", "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears." }, "entity": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity", "description": "Entity to specify the object category that this track is labeled as." }, "version": { "type": "string", "description": "Feature version." }, "confidence": { "description": "Object category's labeling confidence of this track.", "format": "float", "type": "number" }, "frames": { "type": "array", "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingFrame" } } }, "id": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingAnnotation", "description": "Annotations corresponding to one tracked object." }, "GoogleCloudVideointelligenceV1beta2_VideoAnnotationProgress": { "description": "Annotation progress for a single video.", "type": "object", "properties": { "updateTime": { "type": "string", "description": "Time of the most recent update.", "format": "google-datetime" }, "inputUri": { "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", "type": "string" }, "feature": { "type": "string", "description": "Specifies which feature is being tracked if the request contains more than one feature.", "enum": [ "FEATURE_UNSPECIFIED", "LABEL_DETECTION", "SHOT_CHANGE_DETECTION", "EXPLICIT_CONTENT_DETECTION", "FACE_DETECTION", "SPEECH_TRANSCRIPTION", "TEXT_DETECTION", "OBJECT_TRACKING", "LOGO_RECOGNITION", "PERSON_DETECTION" ], "enumDescriptions": [ "Unspecified.", "Label detection. Detect objects, such as dog or flower.", "Shot change detection.", "Explicit content detection.", "Human face detection.", "Speech transcription.", "OCR text detection and tracking.", "Object detection and tracking.", "Logo detection, tracking, and recognition.", "Person detection." ] }, "exportStatus": { "$ref": "GoogleCloudVideointelligenceV1beta2_ExportToOutputUriStatus", "description": "Status of exporting annotation response to user specified `output_uri`. Only set if `output_uri` is set in the request." }, "progressPercent": { "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.", "format": "int32", "type": "integer" }, "startTime": { "type": "string", "description": "Time when the request was received.", "format": "google-datetime" }, "segment": { "description": "Specifies which segment is being tracked if the request contains more than one segment.", "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" } }, "id": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationProgress" }, "GoogleCloudVideointelligenceV1_TextSegment": { "description": "Video segment level annotation results for text detection.", "type": "object", "properties": { "segment": { "description": "Video segment where a text snippet was detected.", "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" }, "confidence": { "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears.", "format": "float", "type": "number" }, "frames": { "description": "Information related to the frames where OCR detected text appears.", "items": { "$ref": "GoogleCloudVideointelligenceV1_TextFrame" }, "type": "array" } }, "id": "GoogleCloudVideointelligenceV1_TextSegment" }, "GoogleCloudVideointelligenceV1p3beta1_VideoSegment": { "id": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment", "type": "object", "properties": { "startTimeOffset": { "type": "string", "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive).", "format": "google-duration" }, "endTimeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).", "format": "google-duration", "type": "string" } }, "description": "Video segment." }, "GoogleCloudVideointelligenceV1p1beta1_ShotChangeDetectionConfig": { "id": "GoogleCloudVideointelligenceV1p1beta1_ShotChangeDetectionConfig", "type": "object", "properties": { "model": { "type": "string", "description": "Model to use for shot change detection. Supported values: \"builtin/stable\" (the default if unset), \"builtin/latest\", and \"builtin/legacy\"." } }, "description": "Config for SHOT_CHANGE_DETECTION." }, "GoogleCloudVideointelligenceV1p1beta1_WordInfo": { "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`.", "id": "GoogleCloudVideointelligenceV1p1beta1_WordInfo", "type": "object", "properties": { "confidence": { "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "format": "float", "readOnly": true, "type": "number" }, "endTime": { "type": "string", "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "format": "google-duration" }, "speakerLabel": { "readOnly": true, "description": "Output only. A distinct string value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word.", "type": "string" }, "startTime": { "type": "string", "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "format": "google-duration" }, "word": { "description": "The word corresponding to this set of information.", "type": "string" }, "speakerTag": { "readOnly": true, "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.", "format": "int32", "type": "integer" } } }, "GoogleCloudVideointelligenceV1p3beta1_CelebrityRecognitionAnnotation": { "description": "Celebrity recognition annotation per video.", "id": "GoogleCloudVideointelligenceV1p3beta1_CelebrityRecognitionAnnotation", "type": "object", "properties": { "celebrityTracks": { "description": "The tracks detected from the input video, including recognized celebrities and other detected faces in the video.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_CelebrityTrack" }, "type": "array" }, "version": { "type": "string", "description": "Feature version." } } }, "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation": { "description": "Label annotation.", "type": "object", "properties": { "categoryEntities": { "type": "array", "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity" } }, "segments": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelSegment" }, "description": "All video segments where a label was detected.", "type": "array" }, "entity": { "description": "Detected entity.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity" }, "version": { "type": "string", "description": "Feature version." }, "frames": { "description": "All video frames where a label was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelFrame" }, "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation" }, "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingFrame": { "id": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingFrame", "type": "object", "properties": { "timeOffset": { "description": "The timestamp of the frame in microseconds.", "format": "google-duration", "type": "string" }, "normalizedBoundingBox": { "description": "The normalized bounding box location of this object track for the frame.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox" } }, "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence." }, "GoogleCloudVideointelligenceV1p2beta1_Track": { "id": "GoogleCloudVideointelligenceV1p2beta1_Track", "type": "object", "properties": { "attributes": { "type": "array", "description": "Optional. Attributes in the track level.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_DetectedAttribute" } }, "timestampedObjects": { "description": "The object with timestamp and attributes per frame in the track.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_TimestampedObject" }, "type": "array" }, "confidence": { "description": "Optional. The confidence score of the tracked object.", "format": "float", "type": "number" }, "segment": { "description": "Video segment of a track.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" } }, "description": "A track of an object instance." }, "GoogleCloudVideointelligenceV1p1beta1_LabelFrame": { "description": "Video frame level annotation results for label detection.", "type": "object", "properties": { "timeOffset": { "type": "string", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "format": "google-duration" }, "confidence": { "type": "number", "description": "Confidence that the label is accurate. Range: [0, 1].", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_LabelFrame" }, "GoogleCloudVideointelligenceV1p1beta1_FaceAnnotation": { "description": "Deprecated. No effect.", "id": "GoogleCloudVideointelligenceV1p1beta1_FaceAnnotation", "deprecated": true, "type": "object", "properties": { "segments": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceSegment" }, "description": "All video segments where a face was detected.", "type": "array" }, "frames": { "description": "All video frames where a face was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceFrame" }, "type": "array" }, "thumbnail": { "type": "string", "description": "Thumbnail of a representative face view (in JPEG format).", "format": "byte" } } }, "GoogleCloudVideointelligenceV1p2beta1_DetectedAttribute": { "description": "A generic detected attribute represented by name in string format.", "type": "object", "properties": { "name": { "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document.", "type": "string" }, "value": { "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc.", "type": "string" }, "confidence": { "description": "Detected attribute confidence. Range [0, 1].", "format": "float", "type": "number" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_DetectedAttribute" }, "GoogleCloudVideointelligenceV1beta2_NormalizedVertex": { "type": "object", "properties": { "x": { "description": "X coordinate.", "format": "float", "type": "number" }, "y": { "description": "Y coordinate.", "format": "float", "type": "number" } }, "id": "GoogleCloudVideointelligenceV1beta2_NormalizedVertex", "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1." }, "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoResponse": { "type": "object", "properties": { "annotationResults": { "type": "array", "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationResults" } } }, "id": "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoResponse", "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service." }, "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox": { "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1].", "type": "object", "properties": { "left": { "description": "Left X coordinate.", "format": "float", "type": "number" }, "top": { "description": "Top Y coordinate.", "format": "float", "type": "number" }, "right": { "type": "number", "description": "Right X coordinate.", "format": "float" }, "bottom": { "type": "number", "description": "Bottom Y coordinate.", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox" }, "GoogleCloudVideointelligenceV1_VideoAnnotationResults": { "description": "Annotation results for a single video.", "id": "GoogleCloudVideointelligenceV1_VideoAnnotationResults", "type": "object", "properties": { "segment": { "$ref": "GoogleCloudVideointelligenceV1_VideoSegment", "description": "Video segment on which the annotation is run." }, "shotLabelAnnotations": { "description": "Topical label annotations on shot level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation" }, "type": "array" }, "textAnnotations": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_TextAnnotation" }, "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it." }, "faceDetectionAnnotations": { "type": "array", "description": "Face detection annotations.", "items": { "$ref": "GoogleCloudVideointelligenceV1_FaceDetectionAnnotation" } }, "objectAnnotations": { "type": "array", "description": "Annotations for list of objects detected and tracked in video.", "items": { "$ref": "GoogleCloudVideointelligenceV1_ObjectTrackingAnnotation" } }, "error": { "$ref": "GoogleRpc_Status", "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail." }, "logoRecognitionAnnotations": { "description": "Annotations for list of logos detected, tracked and recognized in video.", "items": { "$ref": "GoogleCloudVideointelligenceV1_LogoRecognitionAnnotation" }, "type": "array" }, "shotAnnotations": { "description": "Shot annotations. Each shot is represented as a video segment.", "items": { "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" }, "type": "array" }, "explicitAnnotation": { "$ref": "GoogleCloudVideointelligenceV1_ExplicitContentAnnotation", "description": "Explicit content annotation." }, "shotPresenceLabelAnnotations": { "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "items": { "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation" }, "type": "array" }, "faceAnnotations": { "description": "Deprecated. Please use `face_detection_annotations` instead.", "items": { "$ref": "GoogleCloudVideointelligenceV1_FaceAnnotation" }, "deprecated": true, "type": "array" }, "personDetectionAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1_PersonDetectionAnnotation" }, "description": "Person detection annotations.", "type": "array" }, "segmentPresenceLabelAnnotations": { "type": "array", "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "items": { "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation" } }, "inputUri": { "type": "string", "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/)." }, "frameLabelAnnotations": { "description": "Label annotations on frame level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation" }, "type": "array" }, "segmentLabelAnnotations": { "type": "array", "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation" } }, "speechTranscriptions": { "type": "array", "description": "Speech transcription.", "items": { "$ref": "GoogleCloudVideointelligenceV1_SpeechTranscription" } } } }, "GoogleCloudVideointelligenceV1p1beta1_Track": { "type": "object", "properties": { "segment": { "description": "Video segment of a track.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" }, "confidence": { "type": "number", "description": "Optional. The confidence score of the tracked object.", "format": "float" }, "timestampedObjects": { "type": "array", "description": "The object with timestamp and attributes per frame in the track.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_TimestampedObject" } }, "attributes": { "description": "Optional. Attributes in the track level.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_DetectedAttribute" }, "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_Track", "description": "A track of an object instance." }, "GoogleCloudVideointelligenceV1beta2_ObjectTrackingFrame": { "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence.", "type": "object", "properties": { "normalizedBoundingBox": { "description": "The normalized bounding box location of this object track for the frame.", "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox" }, "timeOffset": { "description": "The timestamp of the frame in microseconds.", "format": "google-duration", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingFrame" }, "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoRequest": { "description": "Video annotation request.", "type": "object", "properties": { "locationId": { "description": "Optional. Cloud region where annotation should take place. Supported cloud regions are: `us-east1`, `us-west1`, `europe-west1`, `asia-east1`. If no region is specified, the region will be determined based on video file location.", "type": "string" }, "videoContext": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoContext", "description": "Additional video context and/or feature-specific parameters." }, "inputContent": { "description": "The video data bytes. If unset, the input video(s) should be specified via the `input_uri`. If set, `input_uri` must be unset.", "format": "byte", "type": "string" }, "features": { "type": "array", "description": "Required. Requested video annotation features.", "items": { "enum": [ "FEATURE_UNSPECIFIED", "LABEL_DETECTION", "SHOT_CHANGE_DETECTION", "EXPLICIT_CONTENT_DETECTION", "FACE_DETECTION", "SPEECH_TRANSCRIPTION", "TEXT_DETECTION", "OBJECT_TRACKING", "LOGO_RECOGNITION", "PERSON_DETECTION" ], "enumDescriptions": [ "Unspecified.", "Label detection. Detect objects, such as dog or flower.", "Shot change detection.", "Explicit content detection.", "Human face detection.", "Speech transcription.", "OCR text detection and tracking.", "Object detection and tracking.", "Logo detection, tracking, and recognition.", "Person detection." ], "type": "string" } }, "inputUri": { "description": "Input video location. Currently, only [Cloud Storage](https://cloud.google.com/storage/) URIs are supported. URIs must be specified in the following format: `gs://bucket-id/object-id` (other URI formats return google.rpc.Code.INVALID_ARGUMENT). For more information, see [Request URIs](https://cloud.google.com/storage/docs/request-endpoints). To identify multiple videos, a video URI may include wildcards in the `object-id`. Supported wildcards: '*' to match 0 or more characters; '?' to match 1 character. If unset, the input video should be embedded in the request as `input_content`. If set, `input_content` must be unset.", "type": "string" }, "outputUri": { "description": "Optional. Location where the output (in JSON format) should be stored. Currently, only [Cloud Storage](https://cloud.google.com/storage/) URIs are supported. These must be specified in the following format: `gs://bucket-id/object-id` (other URI formats return google.rpc.Code.INVALID_ARGUMENT). For more information, see [Request URIs](https://cloud.google.com/storage/docs/request-endpoints).", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoRequest" }, "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentFrame": { "type": "object", "properties": { "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "format": "google-duration", "type": "string" }, "pornographyLikelihood": { "type": "string", "enumDescriptions": [ "Unspecified likelihood.", "Very unlikely.", "Unlikely.", "Possible.", "Likely.", "Very likely." ], "description": "Likelihood of the pornography content..", "enum": [ "LIKELIHOOD_UNSPECIFIED", "VERY_UNLIKELY", "UNLIKELY", "POSSIBLE", "LIKELY", "VERY_LIKELY" ] } }, "id": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentFrame", "description": "Video frame level annotation results for explicit content." }, "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingAnnotation": { "description": "Annotations corresponding to one tracked object.", "id": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingAnnotation", "type": "object", "properties": { "confidence": { "description": "Object category's labeling confidence of this track.", "format": "float", "type": "number" }, "frames": { "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingFrame" }, "type": "array" }, "entity": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_Entity", "description": "Entity to specify the object category that this track is labeled as." }, "version": { "type": "string", "description": "Feature version." }, "segment": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment", "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears." }, "trackId": { "type": "string", "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time.", "format": "int64" } } }, "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingFrame": { "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence.", "type": "object", "properties": { "timeOffset": { "type": "string", "description": "The timestamp of the frame in microseconds.", "format": "google-duration" }, "normalizedBoundingBox": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox", "description": "The normalized bounding box location of this object track for the frame." } }, "id": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingFrame" }, "GoogleCloudVideointelligenceV1p3beta1_DetectedAttribute": { "id": "GoogleCloudVideointelligenceV1p3beta1_DetectedAttribute", "type": "object", "properties": { "value": { "type": "string", "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc." }, "name": { "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document.", "type": "string" }, "confidence": { "description": "Detected attribute confidence. Range [0, 1].", "format": "float", "type": "number" } }, "description": "A generic detected attribute represented by name in string format." }, "GoogleCloudVideointelligenceV1p1beta1_VideoContext": { "description": "Video context and/or feature-specific parameters.", "id": "GoogleCloudVideointelligenceV1p1beta1_VideoContext", "type": "object", "properties": { "segments": { "description": "Video segments to annotate. The segments may overlap and are not required to be contiguous or span the whole video. If unspecified, each video is treated as a single segment.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" }, "type": "array" }, "shotChangeDetectionConfig": { "description": "Config for SHOT_CHANGE_DETECTION.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_ShotChangeDetectionConfig" }, "faceDetectionConfig": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceDetectionConfig", "description": "Config for FACE_DETECTION." }, "speechTranscriptionConfig": { "description": "Config for SPEECH_TRANSCRIPTION.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscriptionConfig" }, "labelDetectionConfig": { "description": "Config for LABEL_DETECTION.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelDetectionConfig" }, "explicitContentDetectionConfig": { "description": "Config for EXPLICIT_CONTENT_DETECTION.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentDetectionConfig" }, "textDetectionConfig": { "description": "Config for TEXT_DETECTION.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_TextDetectionConfig" }, "personDetectionConfig": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_PersonDetectionConfig", "description": "Config for PERSON_DETECTION." }, "objectTrackingConfig": { "description": "Config for OBJECT_TRACKING.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingConfig" } } }, "GoogleCloudVideointelligenceV1p2beta1_WordInfo": { "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`.", "type": "object", "properties": { "word": { "type": "string", "description": "The word corresponding to this set of information." }, "speakerTag": { "type": "integer", "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.", "format": "int32", "readOnly": true }, "startTime": { "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "format": "google-duration", "type": "string" }, "speakerLabel": { "readOnly": true, "description": "Output only. A distinct string value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word.", "type": "string" }, "endTime": { "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "format": "google-duration", "type": "string" }, "confidence": { "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "format": "float", "readOnly": true, "type": "number" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_WordInfo" }, "GoogleCloudVideointelligenceV1_SpeechRecognitionAlternative": { "id": "GoogleCloudVideointelligenceV1_SpeechRecognitionAlternative", "type": "object", "properties": { "confidence": { "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "format": "float", "readOnly": true, "type": "number" }, "transcript": { "description": "Transcript text representing the words that the user spoke.", "type": "string" }, "words": { "type": "array", "readOnly": true, "items": { "$ref": "GoogleCloudVideointelligenceV1_WordInfo" }, "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio." } }, "description": "Alternative hypotheses (a.k.a. n-best list)." }, "GoogleCloudVideointelligenceV1beta2_LogoRecognitionAnnotation": { "description": "Annotation corresponding to one detected, tracked and recognized logo class.", "type": "object", "properties": { "tracks": { "type": "array", "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_Track" } }, "segments": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" }, "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment." }, "entity": { "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as.", "$ref": "GoogleCloudVideointelligenceV1beta2_Entity" } }, "id": "GoogleCloudVideointelligenceV1beta2_LogoRecognitionAnnotation" }, "GoogleCloudVideointelligenceV1beta2_AnnotateVideoProgress": { "id": "GoogleCloudVideointelligenceV1beta2_AnnotateVideoProgress", "type": "object", "properties": { "annotationProgress": { "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationProgress" }, "type": "array" } }, "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service." }, "GoogleCloudVideointelligenceV1p1beta1_ExportToOutputUriStatus": { "description": "Status of exporting annotation response to user specified `output_uri`.", "type": "object", "properties": { "status": { "$ref": "GoogleRpc_Status", "description": "Output only. Only set if state is FAILED.", "readOnly": true }, "state": { "type": "string", "description": "Output only. State of the `output_uri` export.", "enum": [ "STATE_UNSPECIFIED", "SUCCEEDED", "FAILED" ], "enumDescriptions": [ "Default value.", "Export succeeded.", "Export failed." ], "readOnly": true } }, "id": "GoogleCloudVideointelligenceV1p1beta1_ExportToOutputUriStatus" }, "GoogleCloudVideointelligenceV1p2beta1_SpeechRecognitionAlternative": { "description": "Alternative hypotheses (a.k.a. n-best list).", "type": "object", "properties": { "transcript": { "type": "string", "description": "Transcript text representing the words that the user spoke." }, "words": { "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio.", "readOnly": true, "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_WordInfo" }, "type": "array" }, "confidence": { "readOnly": true, "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "format": "float", "type": "number" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_SpeechRecognitionAlternative" }, "GoogleCloudVideointelligenceV1p1beta1_FaceDetectionAnnotation": { "description": "Face detection annotation.", "type": "object", "properties": { "thumbnail": { "type": "string", "description": "The thumbnail of a person's face.", "format": "byte" }, "tracks": { "type": "array", "description": "The face tracks with attributes.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_Track" } }, "version": { "type": "string", "description": "Feature version." } }, "id": "GoogleCloudVideointelligenceV1p1beta1_FaceDetectionAnnotation" }, "GoogleCloudVideointelligenceV1_AnnotateVideoResponse": { "type": "object", "properties": { "annotationResults": { "type": "array", "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.", "items": { "$ref": "GoogleCloudVideointelligenceV1_VideoAnnotationResults" } } }, "id": "GoogleCloudVideointelligenceV1_AnnotateVideoResponse", "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service." }, "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationResults": { "id": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationResults", "type": "object", "properties": { "logoRecognitionAnnotations": { "description": "Annotations for list of logos detected, tracked and recognized in video.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LogoRecognitionAnnotation" }, "type": "array" }, "shotAnnotations": { "description": "Shot annotations. Each shot is represented as a video segment.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" }, "type": "array" }, "explicitAnnotation": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentAnnotation", "description": "Explicit content annotation." }, "faceDetectionAnnotations": { "description": "Face detection annotations.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_FaceDetectionAnnotation" }, "type": "array" }, "objectAnnotations": { "description": "Annotations for list of objects detected and tracked in video.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingAnnotation" }, "type": "array" }, "error": { "$ref": "GoogleRpc_Status", "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail." }, "textAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_TextAnnotation" }, "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it.", "type": "array" }, "segment": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment", "description": "Video segment on which the annotation is run." }, "shotLabelAnnotations": { "type": "array", "description": "Topical label annotations on shot level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation" } }, "segmentLabelAnnotations": { "type": "array", "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation" } }, "speechTranscriptions": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_SpeechTranscription" }, "description": "Speech transcription." }, "segmentPresenceLabelAnnotations": { "type": "array", "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation" } }, "inputUri": { "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", "type": "string" }, "frameLabelAnnotations": { "description": "Label annotations on frame level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation" }, "type": "array" }, "faceAnnotations": { "description": "Deprecated. Please use `face_detection_annotations` instead.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_FaceAnnotation" }, "deprecated": true, "type": "array" }, "personDetectionAnnotations": { "description": "Person detection annotations.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_PersonDetectionAnnotation" }, "type": "array" }, "shotPresenceLabelAnnotations": { "type": "array", "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation" } } }, "description": "Annotation results for a single video." }, "GoogleCloudVideointelligenceV1p3beta1_StreamingAnnotateVideoResponse": { "description": "`StreamingAnnotateVideoResponse` is the only message returned to the client by `StreamingAnnotateVideo`. A series of zero or more `StreamingAnnotateVideoResponse` messages are streamed back to the client.", "id": "GoogleCloudVideointelligenceV1p3beta1_StreamingAnnotateVideoResponse", "type": "object", "properties": { "annotationResultsUri": { "type": "string", "description": "Google Cloud Storage URI that stores annotation results of one streaming session in JSON format. It is the annotation_result_storage_directory from the request followed by '/cloud_project_number-session_id'." }, "error": { "description": "If set, returns a google.rpc.Status message that specifies the error for the operation.", "$ref": "GoogleRpc_Status" }, "annotationResults": { "description": "Streaming annotation results.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_StreamingVideoAnnotationResults" } } }, "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscriptionConfig": { "description": "Config for SPEECH_TRANSCRIPTION.", "id": "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscriptionConfig", "type": "object", "properties": { "languageCode": { "description": "Required. *Required* The language of the supplied audio as a [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag. Example: \"en-US\". See [Language Support](https://cloud.google.com/speech/docs/languages) for a list of the currently supported language codes.", "type": "string" }, "enableAutomaticPunctuation": { "type": "boolean", "description": "Optional. If 'true', adds punctuation to recognition result hypotheses. This feature is only available in select languages. Setting this for requests in other languages has no effect at all. The default 'false' value does not add punctuation to result hypotheses. NOTE: \"This is currently offered as an experimental service, complimentary to all users. In the future this may be exclusively available as a premium feature.\"" }, "maxAlternatives": { "type": "integer", "description": "Optional. Maximum number of recognition hypotheses to be returned. Specifically, the maximum number of `SpeechRecognitionAlternative` messages within each `SpeechTranscription`. The server may return fewer than `max_alternatives`. Valid values are `0`-`30`. A value of `0` or `1` will return a maximum of one. If omitted, will return a maximum of one.", "format": "int32" }, "enableSpeakerDiarization": { "description": "Optional. If 'true', enables speaker detection for each recognized word in the top alternative of the recognition result using a speaker_tag provided in the WordInfo. Note: When this is true, we send all the words from the beginning of the audio for the top alternative in every consecutive response. This is done in order to improve our speaker tags as our models learn to identify the speakers in the conversation over time.", "type": "boolean" }, "diarizationSpeakerCount": { "description": "Optional. If set, specifies the estimated number of speakers in the conversation. If not set, defaults to '2'. Ignored unless enable_speaker_diarization is set to true.", "format": "int32", "type": "integer" }, "enableWordConfidence": { "description": "Optional. If `true`, the top result includes a list of words and the confidence for those words. If `false`, no word-level confidence information is returned. The default is `false`.", "type": "boolean" }, "filterProfanity": { "type": "boolean", "description": "Optional. If set to `true`, the server will attempt to filter out profanities, replacing all but the initial character in each filtered word with asterisks, e.g. \"f***\". If set to `false` or omitted, profanities won't be filtered out." }, "audioOutputUriPrefix": { "description": "Optional. Legacy field. This field must be a Cloud Storage URI prefix. (e.g., `gs://bucket/path/`).", "type": "string" }, "audioTracks": { "type": "array", "description": "Optional. For file formats, such as MXF or MKV, supporting multiple audio tracks, specify up to two tracks. Default: track 0.", "items": { "type": "integer", "format": "int32" } }, "speechContexts": { "description": "Optional. A means to provide context to assist the speech recognition.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_SpeechContext" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1beta2_ExplicitContentFrame": { "id": "GoogleCloudVideointelligenceV1beta2_ExplicitContentFrame", "type": "object", "properties": { "timeOffset": { "type": "string", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "format": "google-duration" }, "pornographyLikelihood": { "enumDescriptions": [ "Unspecified likelihood.", "Very unlikely.", "Unlikely.", "Possible.", "Likely.", "Very likely." ], "description": "Likelihood of the pornography content..", "enum": [ "LIKELIHOOD_UNSPECIFIED", "VERY_UNLIKELY", "UNLIKELY", "POSSIBLE", "LIKELY", "VERY_LIKELY" ], "type": "string" } }, "description": "Video frame level annotation results for explicit content." }, "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentFrame": { "description": "Video frame level annotation results for explicit content.", "type": "object", "properties": { "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "format": "google-duration", "type": "string" }, "pornographyLikelihood": { "enumDescriptions": [ "Unspecified likelihood.", "Very unlikely.", "Unlikely.", "Possible.", "Likely.", "Very likely." ], "description": "Likelihood of the pornography content..", "enum": [ "LIKELIHOOD_UNSPECIFIED", "VERY_UNLIKELY", "UNLIKELY", "POSSIBLE", "LIKELY", "VERY_LIKELY" ], "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentFrame" }, "GoogleCloudVideointelligenceV1p3beta1_SpeechRecognitionAlternative": { "description": "Alternative hypotheses (a.k.a. n-best list).", "type": "object", "properties": { "confidence": { "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "format": "float", "readOnly": true, "type": "number" }, "transcript": { "type": "string", "description": "Transcript text representing the words that the user spoke." }, "words": { "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio.", "readOnly": true, "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_WordInfo" }, "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_SpeechRecognitionAlternative" }, "GoogleCloudVideointelligenceV1p3beta1_LabelSegment": { "type": "object", "properties": { "segment": { "description": "Video segment where a label was detected.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" }, "confidence": { "type": "number", "description": "Confidence that the label is accurate. Range: [0, 1].", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_LabelSegment", "description": "Video segment level annotation results for label detection." }, "GoogleCloudVideointelligenceV1beta2_Track": { "type": "object", "properties": { "timestampedObjects": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_TimestampedObject" }, "description": "The object with timestamp and attributes per frame in the track.", "type": "array" }, "attributes": { "type": "array", "description": "Optional. Attributes in the track level.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_DetectedAttribute" } }, "segment": { "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment", "description": "Video segment of a track." }, "confidence": { "description": "Optional. The confidence score of the tracked object.", "format": "float", "type": "number" } }, "id": "GoogleCloudVideointelligenceV1beta2_Track", "description": "A track of an object instance." }, "GoogleCloudVideointelligenceV1_VideoSegment": { "description": "Video segment.", "id": "GoogleCloudVideointelligenceV1_VideoSegment", "type": "object", "properties": { "startTimeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive).", "format": "google-duration", "type": "string" }, "endTimeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).", "format": "google-duration", "type": "string" } } }, "GoogleCloudVideointelligenceV1p1beta1_TimestampedObject": { "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box.", "type": "object", "properties": { "normalizedBoundingBox": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox", "description": "Normalized Bounding box in a frame, where the object is located." }, "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.", "format": "google-duration", "type": "string" }, "attributes": { "type": "array", "description": "Optional. The attributes of the object in the bounding box.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_DetectedAttribute" } }, "landmarks": { "description": "Optional. The detected landmarks.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_DetectedLandmark" }, "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_TimestampedObject" }, "GoogleCloudVideointelligenceV1p2beta1_SpeechTranscription": { "type": "object", "properties": { "languageCode": { "type": "string", "readOnly": true, "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio." }, "alternatives": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_SpeechRecognitionAlternative" }, "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_SpeechTranscription", "description": "A speech recognition result corresponding to a portion of the audio." }, "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingPoly": { "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trigonometric calculations for location of the box.", "id": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingPoly", "type": "object", "properties": { "vertices": { "description": "Normalized vertices of the bounding polygon.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedVertex" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationResults": { "id": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationResults", "type": "object", "properties": { "speechTranscriptions": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscription" }, "description": "Speech transcription.", "type": "array" }, "segmentLabelAnnotations": { "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation" }, "type": "array" }, "segmentPresenceLabelAnnotations": { "type": "array", "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation" } }, "inputUri": { "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", "type": "string" }, "frameLabelAnnotations": { "description": "Label annotations on frame level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation" }, "type": "array" }, "faceAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceAnnotation" }, "description": "Deprecated. Please use `face_detection_annotations` instead.", "deprecated": true, "type": "array" }, "personDetectionAnnotations": { "description": "Person detection annotations.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_PersonDetectionAnnotation" }, "type": "array" }, "shotPresenceLabelAnnotations": { "type": "array", "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation" } }, "shotAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" }, "description": "Shot annotations. Each shot is represented as a video segment.", "type": "array" }, "explicitAnnotation": { "description": "Explicit content annotation.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentAnnotation" }, "logoRecognitionAnnotations": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LogoRecognitionAnnotation" }, "description": "Annotations for list of logos detected, tracked and recognized in video." }, "objectAnnotations": { "type": "array", "description": "Annotations for list of objects detected and tracked in video.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingAnnotation" } }, "error": { "$ref": "GoogleRpc_Status", "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail." }, "faceDetectionAnnotations": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceDetectionAnnotation" }, "description": "Face detection annotations." }, "textAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_TextAnnotation" }, "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it.", "type": "array" }, "segment": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment", "description": "Video segment on which the annotation is run." }, "shotLabelAnnotations": { "description": "Topical label annotations on shot level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation" }, "type": "array" } }, "description": "Annotation results for a single video." }, "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationProgress": { "id": "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationProgress", "type": "object", "properties": { "progressPercent": { "type": "integer", "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.", "format": "int32" }, "startTime": { "description": "Time when the request was received.", "format": "google-datetime", "type": "string" }, "segment": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment", "description": "Specifies which segment is being tracked if the request contains more than one segment." }, "inputUri": { "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", "type": "string" }, "feature": { "description": "Specifies which feature is being tracked if the request contains more than one feature.", "enum": [ "FEATURE_UNSPECIFIED", "LABEL_DETECTION", "SHOT_CHANGE_DETECTION", "EXPLICIT_CONTENT_DETECTION", "FACE_DETECTION", "SPEECH_TRANSCRIPTION", "TEXT_DETECTION", "OBJECT_TRACKING", "LOGO_RECOGNITION", "CELEBRITY_RECOGNITION", "PERSON_DETECTION" ], "enumDescriptions": [ "Unspecified.", "Label detection. Detect objects, such as dog or flower.", "Shot change detection.", "Explicit content detection.", "Human face detection.", "Speech transcription.", "OCR text detection and tracking.", "Object detection and tracking.", "Logo detection, tracking, and recognition.", "Celebrity recognition.", "Person detection." ], "type": "string" }, "exportStatus": { "description": "Status of exporting annotation response to user specified `output_uri`. Only set if `output_uri` is set in the request.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_ExportToOutputUriStatus" }, "updateTime": { "description": "Time of the most recent update.", "format": "google-datetime", "type": "string" } }, "description": "Annotation progress for a single video." }, "GoogleCloudVideointelligenceV1p3beta1_TextSegment": { "type": "object", "properties": { "confidence": { "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears.", "format": "float", "type": "number" }, "frames": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_TextFrame" }, "description": "Information related to the frames where OCR detected text appears." }, "segment": { "description": "Video segment where a text snippet was detected.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_TextSegment", "description": "Video segment level annotation results for text detection." }, "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentDetectionConfig": { "description": "Config for EXPLICIT_CONTENT_DETECTION.", "type": "object", "properties": { "model": { "description": "Model to use for explicit content detection. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\".", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentDetectionConfig" }, "GoogleCloudVideointelligenceV1beta2_ExportToOutputUriStatus": { "description": "Status of exporting annotation response to user specified `output_uri`.", "type": "object", "properties": { "status": { "description": "Output only. Only set if state is FAILED.", "readOnly": true, "$ref": "GoogleRpc_Status" }, "state": { "readOnly": true, "type": "string", "description": "Output only. State of the `output_uri` export.", "enum": [ "STATE_UNSPECIFIED", "SUCCEEDED", "FAILED" ], "enumDescriptions": [ "Default value.", "Export succeeded.", "Export failed." ] } }, "id": "GoogleCloudVideointelligenceV1beta2_ExportToOutputUriStatus" }, "GoogleCloudVideointelligenceV1p2beta1_TimestampedObject": { "type": "object", "properties": { "landmarks": { "type": "array", "description": "Optional. The detected landmarks.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_DetectedLandmark" } }, "attributes": { "type": "array", "description": "Optional. The attributes of the object in the bounding box.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_DetectedAttribute" } }, "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.", "format": "google-duration", "type": "string" }, "normalizedBoundingBox": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox", "description": "Normalized Bounding box in a frame, where the object is located." } }, "id": "GoogleCloudVideointelligenceV1p2beta1_TimestampedObject", "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box." }, "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingFrame": { "id": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingFrame", "type": "object", "properties": { "timeOffset": { "description": "The timestamp of the frame in microseconds.", "format": "google-duration", "type": "string" }, "normalizedBoundingBox": { "description": "The normalized bounding box location of this object track for the frame.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox" } }, "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence." }, "GoogleCloudVideointelligenceV1beta2_SpeechRecognitionAlternative": { "id": "GoogleCloudVideointelligenceV1beta2_SpeechRecognitionAlternative", "type": "object", "properties": { "confidence": { "type": "number", "readOnly": true, "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "format": "float" }, "transcript": { "description": "Transcript text representing the words that the user spoke.", "type": "string" }, "words": { "type": "array", "readOnly": true, "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_WordInfo" }, "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio." } }, "description": "Alternative hypotheses (a.k.a. n-best list)." }, "GoogleCloudVideointelligenceV1_LabelSegment": { "description": "Video segment level annotation results for label detection.", "id": "GoogleCloudVideointelligenceV1_LabelSegment", "type": "object", "properties": { "confidence": { "type": "number", "description": "Confidence that the label is accurate. Range: [0, 1].", "format": "float" }, "segment": { "description": "Video segment where a label was detected.", "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" } } }, "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoProgress": { "id": "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoProgress", "type": "object", "properties": { "annotationProgress": { "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationProgress" }, "type": "array" } }, "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service." }, "GoogleCloudVideointelligenceV1p2beta1_Entity": { "type": "object", "properties": { "description": { "type": "string", "description": "Textual description, e.g., `Fixed-gear bicycle`." }, "entityId": { "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).", "type": "string" }, "languageCode": { "description": "Language code for `description` in BCP-47 format.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_Entity", "description": "Detected entity from video analysis." }, "GoogleCloudVideointelligenceV1_LabelFrame": { "description": "Video frame level annotation results for label detection.", "type": "object", "properties": { "timeOffset": { "type": "string", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "format": "google-duration" }, "confidence": { "type": "number", "description": "Confidence that the label is accurate. Range: [0, 1].", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1_LabelFrame" }, "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentAnnotation": { "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame.", "type": "object", "properties": { "version": { "description": "Feature version.", "type": "string" }, "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentFrame" }, "description": "All video frames where explicit content was detected.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentAnnotation" }, "GoogleCloudVideointelligenceV1p1beta1_FaceFrame": { "description": "Deprecated. No effect.", "deprecated": true, "type": "object", "properties": { "normalizedBoundingBoxes": { "type": "array", "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox" } }, "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "format": "google-duration", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_FaceFrame" }, "GoogleCloudVideointelligenceV1beta2_SpeechTranscription": { "type": "object", "properties": { "languageCode": { "type": "string", "readOnly": true, "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio." }, "alternatives": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_SpeechRecognitionAlternative" }, "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1beta2_SpeechTranscription", "description": "A speech recognition result corresponding to a portion of the audio." }, "GoogleCloudVideointelligenceV1_PersonDetectionAnnotation": { "type": "object", "properties": { "version": { "description": "Feature version.", "type": "string" }, "tracks": { "description": "The detected tracks of a person.", "items": { "$ref": "GoogleCloudVideointelligenceV1_Track" }, "type": "array" } }, "id": "GoogleCloudVideointelligenceV1_PersonDetectionAnnotation", "description": "Person detection annotation per video." }, "GoogleRpc_Status": { "description": "The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors).", "type": "object", "properties": { "message": { "type": "string", "description": "A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client." }, "code": { "description": "The status code, which should be an enum value of google.rpc.Code.", "format": "int32", "type": "integer" }, "details": { "items": { "type": "object", "additionalProperties": { "type": "any", "description": "Properties of the object. Contains field @type with type URL." } }, "description": "A list of messages that carry the error details. There is a common set of message types for APIs to use.", "type": "array" } }, "id": "GoogleRpc_Status" }, "GoogleCloudVideointelligenceV1_AnnotateVideoProgress": { "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", "type": "object", "properties": { "annotationProgress": { "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.", "items": { "$ref": "GoogleCloudVideointelligenceV1_VideoAnnotationProgress" }, "type": "array" } }, "id": "GoogleCloudVideointelligenceV1_AnnotateVideoProgress" }, "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoResponse": { "id": "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoResponse", "type": "object", "properties": { "annotationResults": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationResults" }, "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.", "type": "array" } }, "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service." }, "GoogleCloudVideointelligenceV1p2beta1_ExportToOutputUriStatus": { "type": "object", "properties": { "state": { "enumDescriptions": [ "Default value.", "Export succeeded.", "Export failed." ], "description": "Output only. State of the `output_uri` export.", "enum": [ "STATE_UNSPECIFIED", "SUCCEEDED", "FAILED" ], "type": "string", "readOnly": true }, "status": { "description": "Output only. Only set if state is FAILED.", "readOnly": true, "$ref": "GoogleRpc_Status" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_ExportToOutputUriStatus", "description": "Status of exporting annotation response to user specified `output_uri`." }, "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationResults": { "description": "Annotation results for a single video.", "id": "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationResults", "type": "object", "properties": { "faceDetectionAnnotations": { "description": "Face detection annotations.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceDetectionAnnotation" }, "type": "array" }, "objectAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingAnnotation" }, "description": "Annotations for list of objects detected and tracked in video.", "type": "array" }, "error": { "$ref": "GoogleRpc_Status", "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail." }, "logoRecognitionAnnotations": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LogoRecognitionAnnotation" }, "description": "Annotations for list of logos detected, tracked and recognized in video." }, "shotAnnotations": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" }, "description": "Shot annotations. Each shot is represented as a video segment." }, "explicitAnnotation": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentAnnotation", "description": "Explicit content annotation." }, "segment": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment", "description": "Video segment on which the annotation is run." }, "shotLabelAnnotations": { "type": "array", "description": "Topical label annotations on shot level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" } }, "textAnnotations": { "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_TextAnnotation" }, "type": "array" }, "segmentPresenceLabelAnnotations": { "type": "array", "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" } }, "inputUri": { "type": "string", "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/)." }, "frameLabelAnnotations": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" }, "description": "Label annotations on frame level. There is exactly one element for each unique label." }, "segmentLabelAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" }, "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label.", "type": "array" }, "speechTranscriptions": { "description": "Speech transcription.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_SpeechTranscription" }, "type": "array" }, "shotPresenceLabelAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" }, "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "type": "array" }, "celebrityRecognitionAnnotations": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_CelebrityRecognitionAnnotation", "description": "Celebrity recognition annotations." }, "faceAnnotations": { "deprecated": true, "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceAnnotation" }, "description": "Deprecated. Please use `face_detection_annotations` instead." }, "personDetectionAnnotations": { "type": "array", "description": "Person detection annotations.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_PersonDetectionAnnotation" } } } }, "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentAnnotation": { "type": "object", "properties": { "version": { "type": "string", "description": "Feature version." }, "frames": { "description": "All video frames where explicit content was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentFrame" }, "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentAnnotation", "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame." }, "GoogleCloudVideointelligenceV1_WordInfo": { "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`.", "id": "GoogleCloudVideointelligenceV1_WordInfo", "type": "object", "properties": { "endTime": { "type": "string", "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "format": "google-duration" }, "confidence": { "type": "number", "readOnly": true, "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "format": "float" }, "speakerLabel": { "readOnly": true, "description": "Output only. A distinct string value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word.", "type": "string" }, "startTime": { "type": "string", "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "format": "google-duration" }, "word": { "description": "The word corresponding to this set of information.", "type": "string" }, "speakerTag": { "readOnly": true, "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.", "format": "int32", "type": "integer" } } }, "GoogleCloudVideointelligenceV1p1beta1_TextDetectionConfig": { "id": "GoogleCloudVideointelligenceV1p1beta1_TextDetectionConfig", "type": "object", "properties": { "languageHints": { "description": "Language hint can be specified if the language to be detected is known a priori. It can increase the accuracy of the detection. Language hint must be language code in BCP-47 format. Automatic language detection is performed if no hint is provided.", "items": { "type": "string" }, "type": "array" }, "model": { "description": "Model to use for text detection. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\".", "type": "string" } }, "description": "Config for TEXT_DETECTION." }, "GoogleCloudVideointelligenceV1beta2_DetectedAttribute": { "type": "object", "properties": { "value": { "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc.", "type": "string" }, "name": { "type": "string", "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document." }, "confidence": { "type": "number", "description": "Detected attribute confidence. Range [0, 1].", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1beta2_DetectedAttribute", "description": "A generic detected attribute represented by name in string format." }, "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingPoly": { "id": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingPoly", "type": "object", "properties": { "vertices": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex" }, "description": "Normalized vertices of the bounding polygon.", "type": "array" } }, "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trigonometric calculations for location of the box." }, "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationProgress": { "type": "object", "properties": { "progressPercent": { "type": "integer", "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.", "format": "int32" }, "startTime": { "type": "string", "description": "Time when the request was received.", "format": "google-datetime" }, "segment": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment", "description": "Specifies which segment is being tracked if the request contains more than one segment." }, "updateTime": { "description": "Time of the most recent update.", "format": "google-datetime", "type": "string" }, "inputUri": { "type": "string", "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/)." }, "feature": { "type": "string", "description": "Specifies which feature is being tracked if the request contains more than one feature.", "enum": [ "FEATURE_UNSPECIFIED", "LABEL_DETECTION", "SHOT_CHANGE_DETECTION", "EXPLICIT_CONTENT_DETECTION", "FACE_DETECTION", "SPEECH_TRANSCRIPTION", "TEXT_DETECTION", "OBJECT_TRACKING", "LOGO_RECOGNITION", "PERSON_DETECTION" ], "enumDescriptions": [ "Unspecified.", "Label detection. Detect objects, such as dog or flower.", "Shot change detection.", "Explicit content detection.", "Human face detection.", "Speech transcription.", "OCR text detection and tracking.", "Object detection and tracking.", "Logo detection, tracking, and recognition.", "Person detection." ] }, "exportStatus": { "description": "Status of exporting annotation response to user specified `output_uri`. Only set if `output_uri` is set in the request.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_ExportToOutputUriStatus" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationProgress", "description": "Annotation progress for a single video." }, "GoogleCloudVideointelligenceV1_NormalizedBoundingBox": { "type": "object", "properties": { "left": { "description": "Left X coordinate.", "format": "float", "type": "number" }, "bottom": { "description": "Bottom Y coordinate.", "format": "float", "type": "number" }, "top": { "type": "number", "description": "Top Y coordinate.", "format": "float" }, "right": { "description": "Right X coordinate.", "format": "float", "type": "number" } }, "id": "GoogleCloudVideointelligenceV1_NormalizedBoundingBox", "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1]." }, "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentFrame": { "description": "Video frame level annotation results for explicit content.", "id": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentFrame", "type": "object", "properties": { "timeOffset": { "type": "string", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "format": "google-duration" }, "pornographyLikelihood": { "enumDescriptions": [ "Unspecified likelihood.", "Very unlikely.", "Unlikely.", "Possible.", "Likely.", "Very likely." ], "description": "Likelihood of the pornography content..", "enum": [ "LIKELIHOOD_UNSPECIFIED", "VERY_UNLIKELY", "UNLIKELY", "POSSIBLE", "LIKELY", "VERY_LIKELY" ], "type": "string" } } }, "GoogleCloudVideointelligenceV1_ExportToOutputUriStatus": { "id": "GoogleCloudVideointelligenceV1_ExportToOutputUriStatus", "type": "object", "properties": { "state": { "type": "string", "description": "Output only. State of the `output_uri` export.", "enum": [ "STATE_UNSPECIFIED", "SUCCEEDED", "FAILED" ], "enumDescriptions": [ "Default value.", "Export succeeded.", "Export failed." ], "readOnly": true }, "status": { "$ref": "GoogleRpc_Status", "description": "Output only. Only set if state is FAILED.", "readOnly": true } }, "description": "Status of exporting annotation response to user specified `output_uri`." }, "GoogleCloudVideointelligenceV1p3beta1_FaceDetectionAnnotation": { "description": "Face detection annotation.", "id": "GoogleCloudVideointelligenceV1p3beta1_FaceDetectionAnnotation", "type": "object", "properties": { "thumbnail": { "description": "The thumbnail of a person's face.", "format": "byte", "type": "string" }, "tracks": { "type": "array", "description": "The face tracks with attributes.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_Track" } }, "version": { "type": "string", "description": "Feature version." } } }, "GoogleCloudVideointelligenceV1beta2_ExplicitContentAnnotation": { "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame.", "id": "GoogleCloudVideointelligenceV1beta2_ExplicitContentAnnotation", "type": "object", "properties": { "version": { "description": "Feature version.", "type": "string" }, "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_ExplicitContentFrame" }, "description": "All video frames where explicit content was detected.", "type": "array" } } }, "GoogleCloudVideointelligenceV1p1beta1_DetectedAttribute": { "type": "object", "properties": { "value": { "type": "string", "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc." }, "name": { "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document.", "type": "string" }, "confidence": { "type": "number", "description": "Detected attribute confidence. Range [0, 1].", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_DetectedAttribute", "description": "A generic detected attribute represented by name in string format." }, "GoogleCloudVideointelligenceV1p3beta1_ExportToOutputUriStatus": { "description": "Status of exporting annotation response to user specified `output_uri`.", "type": "object", "properties": { "status": { "$ref": "GoogleRpc_Status", "readOnly": true, "description": "Output only. Only set if state is FAILED." }, "state": { "description": "Output only. State of the `output_uri` export.", "enum": [ "STATE_UNSPECIFIED", "SUCCEEDED", "FAILED" ], "enumDescriptions": [ "Default value.", "Export succeeded.", "Export failed." ], "type": "string", "readOnly": true } }, "id": "GoogleCloudVideointelligenceV1p3beta1_ExportToOutputUriStatus" }, "GoogleCloudVideointelligenceV1p3beta1_LabelFrame": { "description": "Video frame level annotation results for label detection.", "id": "GoogleCloudVideointelligenceV1p3beta1_LabelFrame", "type": "object", "properties": { "confidence": { "type": "number", "description": "Confidence that the label is accurate. Range: [0, 1].", "format": "float" }, "timeOffset": { "type": "string", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "format": "google-duration" } } }, "GoogleCloudVideointelligenceV1p2beta1_FaceDetectionAnnotation": { "description": "Face detection annotation.", "type": "object", "properties": { "version": { "description": "Feature version.", "type": "string" }, "tracks": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_Track" }, "description": "The face tracks with attributes.", "type": "array" }, "thumbnail": { "description": "The thumbnail of a person's face.", "format": "byte", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_FaceDetectionAnnotation" }, "GoogleCloudVideointelligenceV1p3beta1_Celebrity": { "type": "object", "properties": { "description": { "description": "Textual description of additional information about the celebrity, if applicable.", "type": "string" }, "displayName": { "description": "The celebrity name.", "type": "string" }, "name": { "type": "string", "description": "The resource name of the celebrity. Have the format `video-intelligence/kg-mid` indicates a celebrity from preloaded gallery. kg-mid is the id in Google knowledge graph, which is unique for the celebrity." } }, "id": "GoogleCloudVideointelligenceV1p3beta1_Celebrity", "description": "Celebrity definition." }, "GoogleCloudVideointelligenceV1p1beta1_TextSegment": { "type": "object", "properties": { "segment": { "description": "Video segment where a text snippet was detected.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" }, "confidence": { "type": "number", "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears.", "format": "float" }, "frames": { "type": "array", "description": "Information related to the frames where OCR detected text appears.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_TextFrame" } } }, "id": "GoogleCloudVideointelligenceV1p1beta1_TextSegment", "description": "Video segment level annotation results for text detection." }, "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingPoly": { "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trigonometric calculations for location of the box.", "id": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingPoly", "type": "object", "properties": { "vertices": { "description": "Normalized vertices of the bounding polygon.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1p1beta1_FaceDetectionConfig": { "id": "GoogleCloudVideointelligenceV1p1beta1_FaceDetectionConfig", "type": "object", "properties": { "includeAttributes": { "description": "Whether to enable face attributes detection, such as glasses, dark_glasses, mouth_open etc. Ignored if 'include_bounding_boxes' is set to false.", "type": "boolean" }, "includeBoundingBoxes": { "description": "Whether bounding boxes are included in the face annotation output.", "type": "boolean" }, "model": { "type": "string", "description": "Model to use for face detection. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\"." } }, "description": "Config for FACE_DETECTION." }, "GoogleCloudVideointelligenceV1_Entity": { "description": "Detected entity from video analysis.", "type": "object", "properties": { "languageCode": { "description": "Language code for `description` in BCP-47 format.", "type": "string" }, "description": { "type": "string", "description": "Textual description, e.g., `Fixed-gear bicycle`." }, "entityId": { "type": "string", "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/)." } }, "id": "GoogleCloudVideointelligenceV1_Entity" }, "GoogleCloudVideointelligenceV1beta2_LabelSegment": { "description": "Video segment level annotation results for label detection.", "type": "object", "properties": { "segment": { "description": "Video segment where a label was detected.", "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" }, "confidence": { "type": "number", "description": "Confidence that the label is accurate. Range: [0, 1].", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1beta2_LabelSegment" }, "GoogleCloudVideointelligenceV1p2beta1_VideoSegment": { "type": "object", "properties": { "startTimeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive).", "format": "google-duration", "type": "string" }, "endTimeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).", "format": "google-duration", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment", "description": "Video segment." }, "GoogleCloudVideointelligenceV1_NormalizedBoundingPoly": { "id": "GoogleCloudVideointelligenceV1_NormalizedBoundingPoly", "type": "object", "properties": { "vertices": { "items": { "$ref": "GoogleCloudVideointelligenceV1_NormalizedVertex" }, "description": "Normalized vertices of the bounding polygon.", "type": "array" } }, "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trigonometric calculations for location of the box." }, "GoogleLongrunning_Operation": { "description": "This resource represents a long-running operation that is the result of a network API call.", "type": "object", "properties": { "response": { "type": "object", "description": "The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.", "additionalProperties": { "description": "Properties of the object. Contains field @type with type URL.", "type": "any" } }, "metadata": { "type": "object", "additionalProperties": { "type": "any", "description": "Properties of the object. Contains field @type with type URL." }, "description": "Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any." }, "name": { "type": "string", "description": "The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`." }, "error": { "description": "The error result of the operation in case of failure or cancellation.", "$ref": "GoogleRpc_Status" }, "done": { "type": "boolean", "description": "If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available." } }, "id": "GoogleLongrunning_Operation" }, "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex": { "type": "object", "properties": { "x": { "type": "number", "description": "X coordinate.", "format": "float" }, "y": { "description": "Y coordinate.", "format": "float", "type": "number" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex", "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1." }, "GoogleCloudVideointelligenceV1beta2_PersonDetectionAnnotation": { "description": "Person detection annotation per video.", "type": "object", "properties": { "tracks": { "type": "array", "description": "The detected tracks of a person.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_Track" } }, "version": { "description": "Feature version.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1beta2_PersonDetectionAnnotation" }, "GoogleCloudVideointelligenceV1p3beta1_FaceFrame": { "id": "GoogleCloudVideointelligenceV1p3beta1_FaceFrame", "deprecated": true, "type": "object", "properties": { "normalizedBoundingBoxes": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox" }, "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame.", "type": "array" }, "timeOffset": { "type": "string", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "format": "google-duration" } }, "description": "Deprecated. No effect." }, "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex": { "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.", "type": "object", "properties": { "x": { "description": "X coordinate.", "format": "float", "type": "number" }, "y": { "type": "number", "description": "Y coordinate.", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex" }, "GoogleCloudVideointelligenceV1p2beta1_FaceFrame": { "id": "GoogleCloudVideointelligenceV1p2beta1_FaceFrame", "deprecated": true, "type": "object", "properties": { "normalizedBoundingBoxes": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox" }, "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame." }, "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "format": "google-duration", "type": "string" } }, "description": "Deprecated. No effect." }, "GoogleCloudVideointelligenceV1p2beta1_TextAnnotation": { "type": "object", "properties": { "text": { "description": "The detected text.", "type": "string" }, "segments": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_TextSegment" }, "description": "All video segments where OCR detected text appears." }, "version": { "type": "string", "description": "Feature version." } }, "id": "GoogleCloudVideointelligenceV1p2beta1_TextAnnotation", "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection." }, "GoogleCloudVideointelligenceV1_ObjectTrackingAnnotation": { "description": "Annotations corresponding to one tracked object.", "type": "object", "properties": { "confidence": { "description": "Object category's labeling confidence of this track.", "format": "float", "type": "number" }, "frames": { "type": "array", "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.", "items": { "$ref": "GoogleCloudVideointelligenceV1_ObjectTrackingFrame" } }, "entity": { "description": "Entity to specify the object category that this track is labeled as.", "$ref": "GoogleCloudVideointelligenceV1_Entity" }, "version": { "type": "string", "description": "Feature version." }, "segment": { "$ref": "GoogleCloudVideointelligenceV1_VideoSegment", "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears." }, "trackId": { "type": "string", "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time.", "format": "int64" } }, "id": "GoogleCloudVideointelligenceV1_ObjectTrackingAnnotation" }, "GoogleCloudVideointelligenceV1p1beta1_TextAnnotation": { "type": "object", "properties": { "version": { "description": "Feature version.", "type": "string" }, "text": { "type": "string", "description": "The detected text." }, "segments": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_TextSegment" }, "description": "All video segments where OCR detected text appears.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_TextAnnotation", "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection." }, "GoogleCloudVideointelligenceV1_DetectedAttribute": { "id": "GoogleCloudVideointelligenceV1_DetectedAttribute", "type": "object", "properties": { "value": { "type": "string", "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc." }, "name": { "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document.", "type": "string" }, "confidence": { "type": "number", "description": "Detected attribute confidence. Range [0, 1].", "format": "float" } }, "description": "A generic detected attribute represented by name in string format." }, "GoogleCloudVideointelligenceV1p2beta1_LogoRecognitionAnnotation": { "description": "Annotation corresponding to one detected, tracked and recognized logo class.", "type": "object", "properties": { "tracks": { "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_Track" }, "type": "array" }, "segments": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" }, "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment." }, "entity": { "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_LogoRecognitionAnnotation" }, "GoogleCloudVideointelligenceV1p2beta1_PersonDetectionAnnotation": { "type": "object", "properties": { "tracks": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_Track" }, "description": "The detected tracks of a person.", "type": "array" }, "version": { "type": "string", "description": "Feature version." } }, "id": "GoogleCloudVideointelligenceV1p2beta1_PersonDetectionAnnotation", "description": "Person detection annotation per video." }, "GoogleCloudVideointelligenceV1_TextFrame": { "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.", "id": "GoogleCloudVideointelligenceV1_TextFrame", "type": "object", "properties": { "rotatedBoundingBox": { "description": "Bounding polygon of the detected text for this frame.", "$ref": "GoogleCloudVideointelligenceV1_NormalizedBoundingPoly" }, "timeOffset": { "description": "Timestamp of this frame.", "format": "google-duration", "type": "string" } } }, "GoogleCloudVideointelligenceV1p3beta1_SpeechTranscription": { "id": "GoogleCloudVideointelligenceV1p3beta1_SpeechTranscription", "type": "object", "properties": { "alternatives": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_SpeechRecognitionAlternative" }, "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.", "type": "array" }, "languageCode": { "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.", "readOnly": true, "type": "string" } }, "description": "A speech recognition result corresponding to a portion of the audio." }, "GoogleCloudVideointelligenceV1beta2_DetectedLandmark": { "id": "GoogleCloudVideointelligenceV1beta2_DetectedLandmark", "type": "object", "properties": { "confidence": { "description": "The confidence score of the detected landmark. Range [0, 1].", "format": "float", "type": "number" }, "name": { "type": "string", "description": "The name of this landmark, for example, left_hand, right_shoulder." }, "point": { "description": "The 2D point of the detected landmark using the normalized image coordinate system. The normalized coordinates have the range from 0 to 1.", "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedVertex" } }, "description": "A generic detected landmark represented by name in string format and a 2D location." }, "GoogleCloudVideointelligenceV1beta2_VideoSegment": { "description": "Video segment.", "id": "GoogleCloudVideointelligenceV1beta2_VideoSegment", "type": "object", "properties": { "startTimeOffset": { "type": "string", "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive).", "format": "google-duration" }, "endTimeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).", "format": "google-duration", "type": "string" } } }, "GoogleCloudVideointelligenceV1_ObjectTrackingFrame": { "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence.", "id": "GoogleCloudVideointelligenceV1_ObjectTrackingFrame", "type": "object", "properties": { "normalizedBoundingBox": { "description": "The normalized bounding box location of this object track for the frame.", "$ref": "GoogleCloudVideointelligenceV1_NormalizedBoundingBox" }, "timeOffset": { "type": "string", "description": "The timestamp of the frame in microseconds.", "format": "google-duration" } } }, "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingConfig": { "description": "Config for OBJECT_TRACKING.", "id": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingConfig", "type": "object", "properties": { "model": { "description": "Model to use for object tracking. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\".", "type": "string" } } }, "GoogleCloudVideointelligenceV1beta2_TimestampedObject": { "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box.", "id": "GoogleCloudVideointelligenceV1beta2_TimestampedObject", "type": "object", "properties": { "landmarks": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_DetectedLandmark" }, "description": "Optional. The detected landmarks.", "type": "array" }, "attributes": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_DetectedAttribute" }, "description": "Optional. The attributes of the object in the bounding box.", "type": "array" }, "timeOffset": { "type": "string", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.", "format": "google-duration" }, "normalizedBoundingBox": { "description": "Normalized Bounding box in a frame, where the object is located.", "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox" } } }, "GoogleCloudVideointelligenceV1_Track": { "id": "GoogleCloudVideointelligenceV1_Track", "type": "object", "properties": { "timestampedObjects": { "description": "The object with timestamp and attributes per frame in the track.", "items": { "$ref": "GoogleCloudVideointelligenceV1_TimestampedObject" }, "type": "array" }, "attributes": { "items": { "$ref": "GoogleCloudVideointelligenceV1_DetectedAttribute" }, "description": "Optional. Attributes in the track level.", "type": "array" }, "segment": { "description": "Video segment of a track.", "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" }, "confidence": { "type": "number", "description": "Optional. The confidence score of the tracked object.", "format": "float" } }, "description": "A track of an object instance." }, "GoogleCloudVideointelligenceV1_FaceSegment": { "type": "object", "properties": { "segment": { "description": "Video segment where a face was detected.", "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" } }, "id": "GoogleCloudVideointelligenceV1_FaceSegment", "description": "Video segment level annotation results for face detection." }, "GoogleCloudVideointelligenceV1_ExplicitContentFrame": { "description": "Video frame level annotation results for explicit content.", "type": "object", "properties": { "timeOffset": { "type": "string", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "format": "google-duration" }, "pornographyLikelihood": { "description": "Likelihood of the pornography content..", "enum": [ "LIKELIHOOD_UNSPECIFIED", "VERY_UNLIKELY", "UNLIKELY", "POSSIBLE", "LIKELY", "VERY_LIKELY" ], "enumDescriptions": [ "Unspecified likelihood.", "Very unlikely.", "Unlikely.", "Possible.", "Likely.", "Very likely." ], "type": "string" } }, "id": "GoogleCloudVideointelligenceV1_ExplicitContentFrame" }, "GoogleCloudVideointelligenceV1_VideoAnnotationProgress": { "description": "Annotation progress for a single video.", "type": "object", "properties": { "progressPercent": { "type": "integer", "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.", "format": "int32" }, "startTime": { "description": "Time when the request was received.", "format": "google-datetime", "type": "string" }, "segment": { "description": "Specifies which segment is being tracked if the request contains more than one segment.", "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" }, "updateTime": { "description": "Time of the most recent update.", "format": "google-datetime", "type": "string" }, "inputUri": { "type": "string", "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/)." }, "feature": { "type": "string", "enumDescriptions": [ "Unspecified.", "Label detection. Detect objects, such as dog or flower.", "Shot change detection.", "Explicit content detection.", "Human face detection.", "Speech transcription.", "OCR text detection and tracking.", "Object detection and tracking.", "Logo detection, tracking, and recognition.", "Person detection." ], "description": "Specifies which feature is being tracked if the request contains more than one feature.", "enum": [ "FEATURE_UNSPECIFIED", "LABEL_DETECTION", "SHOT_CHANGE_DETECTION", "EXPLICIT_CONTENT_DETECTION", "FACE_DETECTION", "SPEECH_TRANSCRIPTION", "TEXT_DETECTION", "OBJECT_TRACKING", "LOGO_RECOGNITION", "PERSON_DETECTION" ] }, "exportStatus": { "description": "Status of exporting annotation response to user specified `output_uri`. Only set if `output_uri` is set in the request.", "$ref": "GoogleCloudVideointelligenceV1_ExportToOutputUriStatus" } }, "id": "GoogleCloudVideointelligenceV1_VideoAnnotationProgress" }, "GoogleCloudVideointelligenceV1p3beta1_FaceAnnotation": { "description": "Deprecated. No effect.", "deprecated": true, "type": "object", "properties": { "thumbnail": { "type": "string", "description": "Thumbnail of a representative face view (in JPEG format).", "format": "byte" }, "segments": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceSegment" }, "description": "All video segments where a face was detected.", "type": "array" }, "frames": { "type": "array", "description": "All video frames where a face was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceFrame" } } }, "id": "GoogleCloudVideointelligenceV1p3beta1_FaceAnnotation" }, "GoogleCloudVideointelligenceV1p3beta1_DetectedLandmark": { "description": "A generic detected landmark represented by name in string format and a 2D location.", "id": "GoogleCloudVideointelligenceV1p3beta1_DetectedLandmark", "type": "object", "properties": { "name": { "type": "string", "description": "The name of this landmark, for example, left_hand, right_shoulder." }, "point": { "description": "The 2D point of the detected landmark using the normalized image coordinate system. The normalized coordinates have the range from 0 to 1.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedVertex" }, "confidence": { "description": "The confidence score of the detected landmark. Range [0, 1].", "format": "float", "type": "number" } } }, "GoogleCloudVideointelligenceV1_FaceDetectionAnnotation": { "description": "Face detection annotation.", "id": "GoogleCloudVideointelligenceV1_FaceDetectionAnnotation", "type": "object", "properties": { "version": { "description": "Feature version.", "type": "string" }, "thumbnail": { "type": "string", "description": "The thumbnail of a person's face.", "format": "byte" }, "tracks": { "description": "The face tracks with attributes.", "items": { "$ref": "GoogleCloudVideointelligenceV1_Track" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1_TimestampedObject": { "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box.", "type": "object", "properties": { "landmarks": { "type": "array", "description": "Optional. The detected landmarks.", "items": { "$ref": "GoogleCloudVideointelligenceV1_DetectedLandmark" } }, "attributes": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_DetectedAttribute" }, "description": "Optional. The attributes of the object in the bounding box." }, "timeOffset": { "type": "string", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.", "format": "google-duration" }, "normalizedBoundingBox": { "description": "Normalized Bounding box in a frame, where the object is located.", "$ref": "GoogleCloudVideointelligenceV1_NormalizedBoundingBox" } }, "id": "GoogleCloudVideointelligenceV1_TimestampedObject" }, "GoogleCloudVideointelligenceV1p3beta1_Entity": { "id": "GoogleCloudVideointelligenceV1p3beta1_Entity", "type": "object", "properties": { "languageCode": { "type": "string", "description": "Language code for `description` in BCP-47 format." }, "entityId": { "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).", "type": "string" }, "description": { "type": "string", "description": "Textual description, e.g., `Fixed-gear bicycle`." } }, "description": "Detected entity from video analysis." }, "GoogleCloudVideointelligenceV1p3beta1_TimestampedObject": { "type": "object", "properties": { "landmarks": { "description": "Optional. The detected landmarks.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_DetectedLandmark" }, "type": "array" }, "attributes": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_DetectedAttribute" }, "description": "Optional. The attributes of the object in the bounding box.", "type": "array" }, "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.", "format": "google-duration", "type": "string" }, "normalizedBoundingBox": { "description": "Normalized Bounding box in a frame, where the object is located.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_TimestampedObject", "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box." }, "GoogleCloudVideointelligenceV1p3beta1_PersonDetectionAnnotation": { "description": "Person detection annotation per video.", "id": "GoogleCloudVideointelligenceV1p3beta1_PersonDetectionAnnotation", "type": "object", "properties": { "version": { "type": "string", "description": "Feature version." }, "tracks": { "description": "The detected tracks of a person.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_Track" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1p1beta1_Entity": { "description": "Detected entity from video analysis.", "type": "object", "properties": { "languageCode": { "type": "string", "description": "Language code for `description` in BCP-47 format." }, "description": { "type": "string", "description": "Textual description, e.g., `Fixed-gear bicycle`." }, "entityId": { "type": "string", "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/)." } }, "id": "GoogleCloudVideointelligenceV1p1beta1_Entity" }, "GoogleCloudVideointelligenceV1beta2_LabelFrame": { "type": "object", "properties": { "timeOffset": { "type": "string", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "format": "google-duration" }, "confidence": { "type": "number", "description": "Confidence that the label is accurate. Range: [0, 1].", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1beta2_LabelFrame", "description": "Video frame level annotation results for label detection." }, "GoogleCloudVideointelligenceV1p1beta1_LabelSegment": { "type": "object", "properties": { "segment": { "description": "Video segment where a label was detected.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" }, "confidence": { "type": "number", "description": "Confidence that the label is accurate. Range: [0, 1].", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_LabelSegment", "description": "Video segment level annotation results for label detection." }, "GoogleCloudVideointelligenceV1_TextAnnotation": { "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection.", "type": "object", "properties": { "text": { "description": "The detected text.", "type": "string" }, "segments": { "items": { "$ref": "GoogleCloudVideointelligenceV1_TextSegment" }, "description": "All video segments where OCR detected text appears.", "type": "array" }, "version": { "type": "string", "description": "Feature version." } }, "id": "GoogleCloudVideointelligenceV1_TextAnnotation" }, "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentAnnotation": { "id": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentAnnotation", "type": "object", "properties": { "version": { "type": "string", "description": "Feature version." }, "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentFrame" }, "description": "All video frames where explicit content was detected.", "type": "array" } }, "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame." }, "GoogleCloudVideointelligenceV1beta2_TextSegment": { "description": "Video segment level annotation results for text detection.", "type": "object", "properties": { "confidence": { "type": "number", "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears.", "format": "float" }, "frames": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_TextFrame" }, "description": "Information related to the frames where OCR detected text appears." }, "segment": { "description": "Video segment where a text snippet was detected.", "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" } }, "id": "GoogleCloudVideointelligenceV1beta2_TextSegment" }, "GoogleCloudVideointelligenceV1_LabelAnnotation": { "description": "Label annotation.", "id": "GoogleCloudVideointelligenceV1_LabelAnnotation", "type": "object", "properties": { "categoryEntities": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_Entity" }, "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`." }, "segments": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_LabelSegment" }, "description": "All video segments where a label was detected." }, "entity": { "description": "Detected entity.", "$ref": "GoogleCloudVideointelligenceV1_Entity" }, "version": { "description": "Feature version.", "type": "string" }, "frames": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_LabelFrame" }, "description": "All video frames where a label was detected." } } }, "GoogleCloudVideointelligenceV1beta2_ObjectTrackingAnnotation": { "description": "Annotations corresponding to one tracked object.", "id": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingAnnotation", "type": "object", "properties": { "trackId": { "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time.", "format": "int64", "type": "string" }, "segment": { "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment", "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears." }, "entity": { "$ref": "GoogleCloudVideointelligenceV1beta2_Entity", "description": "Entity to specify the object category that this track is labeled as." }, "version": { "description": "Feature version.", "type": "string" }, "confidence": { "type": "number", "description": "Object category's labeling confidence of this track.", "format": "float" }, "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingFrame" }, "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.", "type": "array" } } }, "GoogleCloudVideointelligenceV1_DetectedLandmark": { "description": "A generic detected landmark represented by name in string format and a 2D location.", "type": "object", "properties": { "name": { "description": "The name of this landmark, for example, left_hand, right_shoulder.", "type": "string" }, "point": { "$ref": "GoogleCloudVideointelligenceV1_NormalizedVertex", "description": "The 2D point of the detected landmark using the normalized image coordinate system. The normalized coordinates have the range from 0 to 1." }, "confidence": { "description": "The confidence score of the detected landmark. Range [0, 1].", "format": "float", "type": "number" } }, "id": "GoogleCloudVideointelligenceV1_DetectedLandmark" }, "GoogleCloudVideointelligenceV1p1beta1_DetectedLandmark": { "description": "A generic detected landmark represented by name in string format and a 2D location.", "id": "GoogleCloudVideointelligenceV1p1beta1_DetectedLandmark", "type": "object", "properties": { "confidence": { "description": "The confidence score of the detected landmark. Range [0, 1].", "format": "float", "type": "number" }, "name": { "type": "string", "description": "The name of this landmark, for example, left_hand, right_shoulder." }, "point": { "description": "The 2D point of the detected landmark using the normalized image coordinate system. The normalized coordinates have the range from 0 to 1.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex" } } }, "GoogleCloudVideointelligenceV1p3beta1_FaceSegment": { "type": "object", "properties": { "segment": { "description": "Video segment where a face was detected.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_FaceSegment", "description": "Video segment level annotation results for face detection." }, "GoogleCloudVideointelligenceV1p1beta1_PersonDetectionConfig": { "description": "Config for PERSON_DETECTION.", "type": "object", "properties": { "includeBoundingBoxes": { "description": "Whether bounding boxes are included in the person detection annotation output.", "type": "boolean" }, "includeAttributes": { "type": "boolean", "description": "Whether to enable person attributes detection, such as cloth color (black, blue, etc), type (coat, dress, etc), pattern (plain, floral, etc), hair, etc. Ignored if 'include_bounding_boxes' is set to false." }, "includePoseLandmarks": { "type": "boolean", "description": "Whether to enable pose landmarks detection. Ignored if 'include_bounding_boxes' is set to false." } }, "id": "GoogleCloudVideointelligenceV1p1beta1_PersonDetectionConfig" }, "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoProgress": { "type": "object", "properties": { "annotationProgress": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationProgress" }, "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoProgress", "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service." }, "GoogleCloudVideointelligenceV1_FaceAnnotation": { "id": "GoogleCloudVideointelligenceV1_FaceAnnotation", "deprecated": true, "type": "object", "properties": { "segments": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_FaceSegment" }, "description": "All video segments where a face was detected." }, "frames": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_FaceFrame" }, "description": "All video frames where a face was detected." }, "thumbnail": { "type": "string", "description": "Thumbnail of a representative face view (in JPEG format).", "format": "byte" } }, "description": "Deprecated. No effect." }, "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoResponse": { "id": "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoResponse", "type": "object", "properties": { "annotationResults": { "type": "array", "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationResults" } } }, "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service." }, "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation": { "type": "object", "properties": { "frames": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelFrame" }, "description": "All video frames where a label was detected." }, "entity": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity", "description": "Detected entity." }, "version": { "description": "Feature version.", "type": "string" }, "categoryEntities": { "type": "array", "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity" } }, "segments": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelSegment" }, "description": "All video segments where a label was detected." } }, "id": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation", "description": "Label annotation." }, "GoogleCloudVideointelligenceV1p2beta1_FaceAnnotation": { "deprecated": true, "type": "object", "properties": { "segments": { "description": "All video segments where a face was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_FaceSegment" }, "type": "array" }, "frames": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_FaceFrame" }, "description": "All video frames where a face was detected." }, "thumbnail": { "description": "Thumbnail of a representative face view (in JPEG format).", "format": "byte", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_FaceAnnotation", "description": "Deprecated. No effect." }, "GoogleCloudVideointelligenceV1p2beta1_TextSegment": { "description": "Video segment level annotation results for text detection.", "id": "GoogleCloudVideointelligenceV1p2beta1_TextSegment", "type": "object", "properties": { "segment": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment", "description": "Video segment where a text snippet was detected." }, "confidence": { "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears.", "format": "float", "type": "number" }, "frames": { "description": "Information related to the frames where OCR detected text appears.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_TextFrame" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1p3beta1_CelebrityTrack": { "id": "GoogleCloudVideointelligenceV1p3beta1_CelebrityTrack", "type": "object", "properties": { "faceTrack": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_Track", "description": "A track of a person's face." }, "celebrities": { "description": "Top N match of the celebrities for the face in this track.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_RecognizedCelebrity" }, "type": "array" } }, "description": "The annotation result of a celebrity face track. RecognizedCelebrity field could be empty if the face track does not have any matched celebrities." }, "GoogleCloudVideointelligenceV1_ExplicitContentAnnotation": { "id": "GoogleCloudVideointelligenceV1_ExplicitContentAnnotation", "type": "object", "properties": { "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1_ExplicitContentFrame" }, "description": "All video frames where explicit content was detected.", "type": "array" }, "version": { "type": "string", "description": "Feature version." } }, "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame." }, "GoogleCloudVideointelligenceV1p2beta1_LabelFrame": { "id": "GoogleCloudVideointelligenceV1p2beta1_LabelFrame", "type": "object", "properties": { "confidence": { "type": "number", "description": "Confidence that the label is accurate. Range: [0, 1].", "format": "float" }, "timeOffset": { "type": "string", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "format": "google-duration" } }, "description": "Video frame level annotation results for label detection." }, "GoogleCloudVideointelligenceV1beta2_VideoAnnotationResults": { "description": "Annotation results for a single video.", "id": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationResults", "type": "object", "properties": { "faceDetectionAnnotations": { "type": "array", "description": "Face detection annotations.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_FaceDetectionAnnotation" } }, "objectAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingAnnotation" }, "description": "Annotations for list of objects detected and tracked in video.", "type": "array" }, "error": { "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail.", "$ref": "GoogleRpc_Status" }, "logoRecognitionAnnotations": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LogoRecognitionAnnotation" }, "description": "Annotations for list of logos detected, tracked and recognized in video." }, "shotAnnotations": { "type": "array", "description": "Shot annotations. Each shot is represented as a video segment.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" } }, "explicitAnnotation": { "$ref": "GoogleCloudVideointelligenceV1beta2_ExplicitContentAnnotation", "description": "Explicit content annotation." }, "segment": { "description": "Video segment on which the annotation is run.", "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" }, "shotLabelAnnotations": { "type": "array", "description": "Topical label annotations on shot level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation" } }, "textAnnotations": { "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_TextAnnotation" }, "type": "array" }, "segmentPresenceLabelAnnotations": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation" }, "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request." }, "inputUri": { "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", "type": "string" }, "frameLabelAnnotations": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation" }, "description": "Label annotations on frame level. There is exactly one element for each unique label." }, "segmentLabelAnnotations": { "type": "array", "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation" } }, "speechTranscriptions": { "description": "Speech transcription.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_SpeechTranscription" }, "type": "array" }, "shotPresenceLabelAnnotations": { "type": "array", "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation" } }, "faceAnnotations": { "deprecated": true, "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_FaceAnnotation" }, "description": "Deprecated. Please use `face_detection_annotations` instead." }, "personDetectionAnnotations": { "description": "Person detection annotations.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_PersonDetectionAnnotation" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1p3beta1_TextFrame": { "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.", "type": "object", "properties": { "rotatedBoundingBox": { "description": "Bounding polygon of the detected text for this frame.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingPoly" }, "timeOffset": { "type": "string", "description": "Timestamp of this frame.", "format": "google-duration" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_TextFrame" }, "GoogleCloudVideointelligenceV1p3beta1_TextAnnotation": { "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection.", "type": "object", "properties": { "text": { "type": "string", "description": "The detected text." }, "segments": { "description": "All video segments where OCR detected text appears.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_TextSegment" }, "type": "array" }, "version": { "type": "string", "description": "Feature version." } }, "id": "GoogleCloudVideointelligenceV1p3beta1_TextAnnotation" }, "GoogleCloudVideointelligenceV1p1beta1_PersonDetectionAnnotation": { "description": "Person detection annotation per video.", "type": "object", "properties": { "version": { "description": "Feature version.", "type": "string" }, "tracks": { "description": "The detected tracks of a person.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_Track" }, "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_PersonDetectionAnnotation" }, "GoogleCloudVideointelligenceV1p3beta1_LogoRecognitionAnnotation": { "description": "Annotation corresponding to one detected, tracked and recognized logo class.", "id": "GoogleCloudVideointelligenceV1p3beta1_LogoRecognitionAnnotation", "type": "object", "properties": { "tracks": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_Track" }, "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames." }, "segments": { "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" }, "type": "array" }, "entity": { "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_Entity" } } }, "GoogleCloudVideointelligenceV1beta2_Entity": { "type": "object", "properties": { "entityId": { "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).", "type": "string" }, "description": { "description": "Textual description, e.g., `Fixed-gear bicycle`.", "type": "string" }, "languageCode": { "description": "Language code for `description` in BCP-47 format.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1beta2_Entity", "description": "Detected entity from video analysis." }, "GoogleCloudVideointelligenceV1p3beta1_StreamingVideoAnnotationResults": { "type": "object", "properties": { "frameTimestamp": { "description": "Timestamp of the processed frame in microseconds.", "format": "google-duration", "type": "string" }, "objectAnnotations": { "type": "array", "description": "Object tracking results.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingAnnotation" } }, "labelAnnotations": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" }, "description": "Label annotation results." }, "explicitAnnotation": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentAnnotation", "description": "Explicit content annotation results." }, "shotAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" }, "description": "Shot annotation results. Each shot is represented as a video segment.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_StreamingVideoAnnotationResults", "description": "Streaming annotation results corresponding to a portion of the video that is currently being processed. Only ONE type of annotation will be specified in the response." }, "GoogleCloudVideointelligenceV1_FaceFrame": { "id": "GoogleCloudVideointelligenceV1_FaceFrame", "deprecated": true, "type": "object", "properties": { "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "format": "google-duration", "type": "string" }, "normalizedBoundingBoxes": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_NormalizedBoundingBox" }, "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame." } }, "description": "Deprecated. No effect." }, "GoogleCloudVideointelligenceV1_LogoRecognitionAnnotation": { "description": "Annotation corresponding to one detected, tracked and recognized logo class.", "id": "GoogleCloudVideointelligenceV1_LogoRecognitionAnnotation", "type": "object", "properties": { "tracks": { "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames.", "items": { "$ref": "GoogleCloudVideointelligenceV1_Track" }, "type": "array" }, "segments": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" }, "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment." }, "entity": { "$ref": "GoogleCloudVideointelligenceV1_Entity", "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as." } } }, "GoogleCloudVideointelligenceV1p2beta1_LabelSegment": { "type": "object", "properties": { "confidence": { "type": "number", "description": "Confidence that the label is accurate. Range: [0, 1].", "format": "float" }, "segment": { "description": "Video segment where a label was detected.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_LabelSegment", "description": "Video segment level annotation results for label detection." }, "GoogleCloudVideointelligenceV1p3beta1_NormalizedVertex": { "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.", "type": "object", "properties": { "x": { "description": "X coordinate.", "format": "float", "type": "number" }, "y": { "description": "Y coordinate.", "format": "float", "type": "number" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_NormalizedVertex" }, "GoogleCloudVideointelligenceV1p2beta1_DetectedLandmark": { "id": "GoogleCloudVideointelligenceV1p2beta1_DetectedLandmark", "type": "object", "properties": { "name": { "description": "The name of this landmark, for example, left_hand, right_shoulder.", "type": "string" }, "point": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex", "description": "The 2D point of the detected landmark using the normalized image coordinate system. The normalized coordinates have the range from 0 to 1." }, "confidence": { "type": "number", "description": "The confidence score of the detected landmark. Range [0, 1].", "format": "float" } }, "description": "A generic detected landmark represented by name in string format and a 2D location." }, "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox": { "id": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox", "type": "object", "properties": { "left": { "description": "Left X coordinate.", "format": "float", "type": "number" }, "top": { "description": "Top Y coordinate.", "format": "float", "type": "number" }, "right": { "type": "number", "description": "Right X coordinate.", "format": "float" }, "bottom": { "type": "number", "description": "Bottom Y coordinate.", "format": "float" } }, "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1]." }, "GoogleCloudVideointelligenceV1p2beta1_FaceSegment": { "id": "GoogleCloudVideointelligenceV1p2beta1_FaceSegment", "type": "object", "properties": { "segment": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment", "description": "Video segment where a face was detected." } }, "description": "Video segment level annotation results for face detection." }, "GoogleCloudVideointelligenceV1beta2_LabelAnnotation": { "id": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation", "type": "object", "properties": { "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LabelFrame" }, "description": "All video frames where a label was detected.", "type": "array" }, "entity": { "description": "Detected entity.", "$ref": "GoogleCloudVideointelligenceV1beta2_Entity" }, "version": { "type": "string", "description": "Feature version." }, "categoryEntities": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_Entity" }, "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`." }, "segments": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LabelSegment" }, "description": "All video segments where a label was detected.", "type": "array" } }, "description": "Label annotation." }, "GoogleCloudVideointelligenceV1beta2_FaceDetectionAnnotation": { "description": "Face detection annotation.", "id": "GoogleCloudVideointelligenceV1beta2_FaceDetectionAnnotation", "type": "object", "properties": { "version": { "type": "string", "description": "Feature version." }, "thumbnail": { "description": "The thumbnail of a person's face.", "format": "byte", "type": "string" }, "tracks": { "description": "The face tracks with attributes.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_Track" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingPoly": { "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trigonometric calculations for location of the box.", "id": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingPoly", "type": "object", "properties": { "vertices": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedVertex" }, "description": "Normalized vertices of the bounding polygon." } } }, "GoogleCloudVideointelligenceV1p1beta1_LabelDetectionConfig": { "type": "object", "properties": { "videoConfidenceThreshold": { "type": "number", "description": "The confidence threshold we perform filtering on the labels from video-level and shot-level detections. If not set, it's set to 0.3 by default. The valid range for this threshold is [0.1, 0.9]. Any value set outside of this range will be clipped. Note: For best results, follow the default threshold. We will update the default threshold everytime when we release a new model.", "format": "float" }, "labelDetectionMode": { "type": "string", "description": "What labels should be detected with LABEL_DETECTION, in addition to video-level labels or segment-level labels. If unspecified, defaults to `SHOT_MODE`.", "enum": [ "LABEL_DETECTION_MODE_UNSPECIFIED", "SHOT_MODE", "FRAME_MODE", "SHOT_AND_FRAME_MODE" ], "enumDescriptions": [ "Unspecified.", "Detect shot-level labels.", "Detect frame-level labels.", "Detect both shot-level and frame-level labels." ] }, "model": { "type": "string", "description": "Model to use for label detection. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\"." }, "stationaryCamera": { "description": "Whether the video has been shot from a stationary (i.e., non-moving) camera. When set to true, might improve detection accuracy for moving objects. Should be used with `SHOT_AND_FRAME_MODE` enabled.", "type": "boolean" }, "frameConfidenceThreshold": { "type": "number", "description": "The confidence threshold we perform filtering on the labels from frame-level detection. If not set, it is set to 0.4 by default. The valid range for this threshold is [0.1, 0.9]. Any value set outside of this range will be clipped. Note: For best results, follow the default threshold. We will update the default threshold everytime when we release a new model.", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_LabelDetectionConfig", "description": "Config for LABEL_DETECTION." }, "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingAnnotation": { "id": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingAnnotation", "type": "object", "properties": { "entity": { "description": "Entity to specify the object category that this track is labeled as.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity" }, "version": { "type": "string", "description": "Feature version." }, "confidence": { "type": "number", "description": "Object category's labeling confidence of this track.", "format": "float" }, "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingFrame" }, "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.", "type": "array" }, "segment": { "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" }, "trackId": { "type": "string", "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time.", "format": "int64" } }, "description": "Annotations corresponding to one tracked object." }, "GoogleCloudVideointelligenceV1p3beta1_WordInfo": { "id": "GoogleCloudVideointelligenceV1p3beta1_WordInfo", "type": "object", "properties": { "confidence": { "type": "number", "readOnly": true, "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "format": "float" }, "endTime": { "type": "string", "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "format": "google-duration" }, "speakerLabel": { "description": "Output only. A distinct string value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word.", "readOnly": true, "type": "string" }, "startTime": { "type": "string", "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "format": "google-duration" }, "word": { "description": "The word corresponding to this set of information.", "type": "string" }, "speakerTag": { "readOnly": true, "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.", "format": "int32", "type": "integer" } }, "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`." }, "GoogleCloudVideointelligenceV1p1beta1_LogoRecognitionAnnotation": { "description": "Annotation corresponding to one detected, tracked and recognized logo class.", "id": "GoogleCloudVideointelligenceV1p1beta1_LogoRecognitionAnnotation", "type": "object", "properties": { "entity": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity", "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as." }, "tracks": { "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_Track" }, "type": "array" }, "segments": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" }, "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment.", "type": "array" } } }, "GoogleCloudVideointelligenceV1p1beta1_TextFrame": { "type": "object", "properties": { "rotatedBoundingBox": { "description": "Bounding polygon of the detected text for this frame.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingPoly" }, "timeOffset": { "type": "string", "description": "Timestamp of this frame.", "format": "google-duration" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_TextFrame", "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets." }, "GoogleCloudVideointelligenceV1_SpeechTranscription": { "description": "A speech recognition result corresponding to a portion of the audio.", "id": "GoogleCloudVideointelligenceV1_SpeechTranscription", "type": "object", "properties": { "languageCode": { "type": "string", "readOnly": true, "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio." }, "alternatives": { "type": "array", "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.", "items": { "$ref": "GoogleCloudVideointelligenceV1_SpeechRecognitionAlternative" } } } }, "GoogleCloudVideointelligenceV1p1beta1_FaceSegment": { "type": "object", "properties": { "segment": { "description": "Video segment where a face was detected.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_FaceSegment", "description": "Video segment level annotation results for face detection." }, "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationProgress": { "id": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationProgress", "type": "object", "properties": { "inputUri": { "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", "type": "string" }, "feature": { "description": "Specifies which feature is being tracked if the request contains more than one feature.", "enum": [ "FEATURE_UNSPECIFIED", "LABEL_DETECTION", "SHOT_CHANGE_DETECTION", "EXPLICIT_CONTENT_DETECTION", "FACE_DETECTION", "SPEECH_TRANSCRIPTION", "TEXT_DETECTION", "OBJECT_TRACKING", "LOGO_RECOGNITION", "PERSON_DETECTION" ], "enumDescriptions": [ "Unspecified.", "Label detection. Detect objects, such as dog or flower.", "Shot change detection.", "Explicit content detection.", "Human face detection.", "Speech transcription.", "OCR text detection and tracking.", "Object detection and tracking.", "Logo detection, tracking, and recognition.", "Person detection." ], "type": "string" }, "exportStatus": { "description": "Status of exporting annotation response to user specified `output_uri`. Only set if `output_uri` is set in the request.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_ExportToOutputUriStatus" }, "updateTime": { "type": "string", "description": "Time of the most recent update.", "format": "google-datetime" }, "progressPercent": { "type": "integer", "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.", "format": "int32" }, "startTime": { "type": "string", "description": "Time when the request was received.", "format": "google-datetime" }, "segment": { "description": "Specifies which segment is being tracked if the request contains more than one segment.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" } }, "description": "Annotation progress for a single video." }, "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscription": { "type": "object", "properties": { "languageCode": { "type": "string", "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.", "readOnly": true }, "alternatives": { "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_SpeechRecognitionAlternative" }, "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer." } }, "id": "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscription", "description": "A speech recognition result corresponding to a portion of the audio." }, "GoogleCloudVideointelligenceV1p1beta1_SpeechRecognitionAlternative": { "description": "Alternative hypotheses (a.k.a. n-best list).", "id": "GoogleCloudVideointelligenceV1p1beta1_SpeechRecognitionAlternative", "type": "object", "properties": { "transcript": { "type": "string", "description": "Transcript text representing the words that the user spoke." }, "words": { "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio.", "readOnly": true, "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_WordInfo" }, "type": "array" }, "confidence": { "type": "number", "readOnly": true, "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "format": "float" } } }, "GoogleCloudVideointelligenceV1p3beta1_RecognizedCelebrity": { "id": "GoogleCloudVideointelligenceV1p3beta1_RecognizedCelebrity", "type": "object", "properties": { "confidence": { "description": "Recognition confidence. Range [0, 1].", "format": "float", "type": "number" }, "celebrity": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_Celebrity", "description": "The recognized celebrity." } }, "description": "The recognized celebrity with confidence score." }, "GoogleCloudVideointelligenceV1beta2_TextAnnotation": { "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection.", "id": "GoogleCloudVideointelligenceV1beta2_TextAnnotation", "type": "object", "properties": { "text": { "type": "string", "description": "The detected text." }, "segments": { "type": "array", "description": "All video segments where OCR detected text appears.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_TextSegment" } }, "version": { "type": "string", "description": "Feature version." } } }, "GoogleCloudVideointelligenceV1_NormalizedVertex": { "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.", "type": "object", "properties": { "x": { "description": "X coordinate.", "format": "float", "type": "number" }, "y": { "description": "Y coordinate.", "format": "float", "type": "number" } }, "id": "GoogleCloudVideointelligenceV1_NormalizedVertex" }, "GoogleCloudVideointelligenceV1beta2_WordInfo": { "type": "object", "properties": { "word": { "type": "string", "description": "The word corresponding to this set of information." }, "speakerTag": { "type": "integer", "readOnly": true, "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.", "format": "int32" }, "startTime": { "type": "string", "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "format": "google-duration" }, "speakerLabel": { "readOnly": true, "description": "Output only. A distinct string value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word.", "type": "string" }, "confidence": { "type": "number", "readOnly": true, "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "format": "float" }, "endTime": { "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "format": "google-duration", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1beta2_WordInfo", "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`." }, "GoogleCloudVideointelligenceV1p2beta1_TextFrame": { "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.", "id": "GoogleCloudVideointelligenceV1p2beta1_TextFrame", "type": "object", "properties": { "rotatedBoundingBox": { "description": "Bounding polygon of the detected text for this frame.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingPoly" }, "timeOffset": { "description": "Timestamp of this frame.", "format": "google-duration", "type": "string" } } }, "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoProgress": { "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", "id": "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoProgress", "type": "object", "properties": { "annotationProgress": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationProgress" }, "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.", "type": "array" } } }, "GoogleCloudVideointelligenceV1beta2_FaceAnnotation": { "id": "GoogleCloudVideointelligenceV1beta2_FaceAnnotation", "deprecated": true, "type": "object", "properties": { "thumbnail": { "type": "string", "description": "Thumbnail of a representative face view (in JPEG format).", "format": "byte" }, "segments": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_FaceSegment" }, "description": "All video segments where a face was detected.", "type": "array" }, "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_FaceFrame" }, "description": "All video frames where a face was detected.", "type": "array" } }, "description": "Deprecated. No effect." }, "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox": { "type": "object", "properties": { "left": { "type": "number", "description": "Left X coordinate.", "format": "float" }, "top": { "description": "Top Y coordinate.", "format": "float", "type": "number" }, "right": { "type": "number", "description": "Right X coordinate.", "format": "float" }, "bottom": { "type": "number", "description": "Bottom Y coordinate.", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox", "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1]." }, "GoogleCloudVideointelligenceV1beta2_FaceSegment": { "description": "Video segment level annotation results for face detection.", "id": "GoogleCloudVideointelligenceV1beta2_FaceSegment", "type": "object", "properties": { "segment": { "description": "Video segment where a face was detected.", "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" } } }, "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation": { "description": "Label annotation.", "id": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation", "type": "object", "properties": { "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelFrame" }, "description": "All video frames where a label was detected.", "type": "array" }, "entity": { "description": "Detected entity.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_Entity" }, "version": { "description": "Feature version.", "type": "string" }, "categoryEntities": { "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_Entity" }, "type": "array" }, "segments": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelSegment" }, "description": "All video segments where a label was detected.", "type": "array" } } }, "GoogleCloudVideointelligenceV1p1beta1_VideoSegment": { "type": "object", "properties": { "startTimeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive).", "format": "google-duration", "type": "string" }, "endTimeOffset": { "type": "string", "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).", "format": "google-duration" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment", "description": "Video segment." }, "GoogleCloudVideointelligenceV1beta2_AnnotateVideoResponse": { "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", "id": "GoogleCloudVideointelligenceV1beta2_AnnotateVideoResponse", "type": "object", "properties": { "annotationResults": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationResults" }, "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.", "type": "array" } } }, "GoogleCloudVideointelligenceV1p3beta1_Track": { "description": "A track of an object instance.", "id": "GoogleCloudVideointelligenceV1p3beta1_Track", "type": "object", "properties": { "confidence": { "description": "Optional. The confidence score of the tracked object.", "format": "float", "type": "number" }, "segment": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment", "description": "Video segment of a track." }, "attributes": { "type": "array", "description": "Optional. Attributes in the track level.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_DetectedAttribute" } }, "timestampedObjects": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_TimestampedObject" }, "description": "The object with timestamp and attributes per frame in the track.", "type": "array" } } } }, "ownerDomain": "google.com", "version_module": true, "version": "v1p1beta1", "batchPath": "batch", "basePath": "", "baseUrl": "https://videointelligence.googleapis.com/", "name": "videointelligence", "documentationLink": "https://cloud.google.com/video-intelligence/docs/", "ownerName": "Google", "servicePath": "" }