v1p3beta1

Unspecified.

Label detection. Detect objects, such as dog or flower.

Shot change detection.

Explicit content detection.

Speech transcription.

OCR text detection and tracking.

Object detection and tracking.

Logo detection, tracking, and recognition.

Unspecified.

Detect shot-level labels.

Detect frame-level labels.

Detect both shot-level and frame-level labels.

Unspecified likelihood.

Very unlikely.

Unlikely.

Possible.

Likely.

Very likely.

Unspecified.

Label detection. Detect objects, such as dog or flower.

Shot change detection.

Explicit content detection.

Object detection and tracking.

Video classification based on AutoML model.

Object detection and tracking based on AutoML model.

Progress metadata for all videos specified in AnnotateVideoRequest.

This object should have the same structure as VideoAnnotationProgress

Input video location. Currently, only Google Cloud Storage URIs are supported, which 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. A video URI may include wildcards in object-id, and thus identify multiple videos. 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 should be unset.

The video data bytes. If unset, the input video(s) should be specified via input_uri. If set, input_uri should be unset.

Requested video annotation features.

The number should be among the values of Feature

Additional video context and/or feature-specific parameters.

This object should have the same structure as VideoContext

Optional location where the output (in JSON format) should be stored. Currently, only Google Cloud Storage URIs are supported, which 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.

Optional cloud region where annotation should take place. Supported cloud regions: us-east1, us-west1, europe-west1, asia-east1. If no region is specified, a region will be determined based on video file location.

Annotation results for all videos specified in AnnotateVideoRequest.

This object should have the same structure as VideoAnnotationResults

The name of the attribute, i.e. glasses, dark_glasses, mouth_open etc. A full list of supported type names will be provided in the document.

Detected attribute confidence. Range [0, 1].

Text value of the detection result. For example, the value for "HairColor" can be "black", "blonde", etc.

Opaque entity ID. Some IDs may be available in Google Knowledge Graph Search API.

Textual description, e.g. Fixed-gear bicycle.

Language code for description in BCP-47 format.

All video frames where explicit content was detected.

This object should have the same structure as ExplicitContentFrame

Model to use for explicit content detection. Supported values: "builtin/stable" (the default if unset) and "builtin/latest".

Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.

This object should have the same structure as Duration

Likelihood of the pornography content..

The number should be among the values of Likelihood

Detected entity.

This object should have the same structure as Entity

Common categories for the detected entity. E.g. 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.

This object should have the same structure as Entity

All video segments where a label was detected.

This object should have the same structure as LabelSegment

All video frames where a label was detected.

This object should have the same structure as LabelFrame

What labels should be detected with LABEL_DETECTION, in addition to video-level labels or segment-level labels. If unspecified, defaults to SHOT_MODE.

The number should be among the values of LabelDetectionMode

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.

Model to use for label detection. Supported values: "builtin/stable" (the default if unset) and "builtin/latest".

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 please follow the default threshold. We will update the default threshold everytime when we release a new model.

The confidence threshold we perform filtering on the labels from video-level and shot-level detections. If not set, it is 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 please follow the default threshold. We will update the default threshold everytime when we release a new model.

Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.

This object should have the same structure as Duration

Confidence that the label is accurate. Range: [0, 1].

Video segment where a label was detected.

This object should have the same structure as VideoSegment

Confidence that the label is accurate. Range: [0, 1].

Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as.

This object should have the same structure as Entity

All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames.

This object should have the same structure as Track

All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment.

This object should have the same structure as VideoSegment

Left X coordinate.

Top Y coordinate.

Right X coordinate.

Bottom Y coordinate.

Normalized vertices of the bounding polygon.

This object should have the same structure as NormalizedVertex

X coordinate.

Y coordinate.

Entity to specify the object category that this track is labeled as.

This object should have the same structure as Entity

Object category's labeling confidence of this track.

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.

This object should have the same structure as ObjectTrackingFrame

Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears.

This object should have the same structure as VideoSegment

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.

Model to use for object tracking. Supported values: "builtin/stable" (the default if unset) and "builtin/latest".

The normalized bounding box location of this object track for the frame.

This object should have the same structure as NormalizedBoundingBox

The timestamp of the frame in microseconds.

This object should have the same structure as Duration

Model to use for shot change detection. Supported values: "builtin/stable" (the default if unset) and "builtin/latest".

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.

Transcript text representing the words that the user spoke.

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 typically provided only for the top hypothesis, and only for is_final=true results. Clients should not rely on the confidence field as it is not guaranteed to be accurate or consistent. The default of 0.0 is a sentinel value indicating confidence was not set.

A list of word-specific information for each recognized word.

This object should have the same structure as WordInfo

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.

This object should have the same structure as SpeechRecognitionAlternative

Output only. The BCP-47 language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.

Required The language of the supplied audio as a BCP-47 language tag. Example: "en-US". See Language Support for a list of the currently supported language codes.

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.

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.

Optional A means to provide context to assist the speech recognition.

This object should have the same structure as SpeechContext

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."

Optional For file formats, such as MXF or MKV, supporting multiple audio tracks, specify up to two tracks. Default: track 0.

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 responses. This is done in order to improve our speaker tags as our models learn to identify the speakers in the conversation over time.

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.

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.

Provides information to the annotator, specifing how to process the request. The first AnnotateStreamingVideoRequest message must only contain a video_config message.

This object should have the same structure as StreamingVideoConfig

The video data to be annotated. Chunks of video data are sequentially sent in StreamingAnnotateVideoRequest messages. Except the initial StreamingAnnotateVideoRequest message containing only video_config, all subsequent AnnotateStreamingVideoRequest messages must only contain input_content field. Note: as with all bytes fields, protobuffers use a pure binary representation (not base64).

If set, returns a google.rpc.Status message that specifies the error for the operation.

This object should have the same structure as Status

Streaming annotation results.

This object should have the same structure as StreamingVideoAnnotationResults

GCS URI that stores annotation results of one streaming session. It is a directory that can hold multiple files in JSON format. Example uri format: gs://bucket_id/object_id/cloud_project_name-session_id

Resource name of AutoML model. Format: projects/{project_id}/locations/{location_id}/models/{model_id}

Resource name of AutoML model. Format: projects/{project_id}/locations/{location_id}/models/{model_id}

Whether the video has been captured from a stationary (i.e. non-moving) camera. When set to true, might improve detection accuracy for moving objects. Default: false.

Enable streaming storage. Default: false.

GCS URI to store all annotation results for one client. Client should specify this field as the top-level storage directory. Annotation results of different sessions will be put into different sub-directories denoted by project_name and session_id. All sub-directories will be auto generated by program and will be made accessible to client in response proto. URIs must be specified in the following format: gs://bucket-id/object-id bucket-id should be a valid GCS bucket created by client and bucket permission shall also be configured properly. object-id can be arbitrary string that make sense to client. Other URI formats will return error and cause GCS write failure.

Shot annotation results. Each shot is represented as a video segment.

This object should have the same structure as VideoSegment

Label annotation results.

This object should have the same structure as LabelAnnotation

Explicit content annotation results.

This object should have the same structure as ExplicitContentAnnotation

Object tracking results.

This object should have the same structure as ObjectTrackingAnnotation

Requested annotation feature.

The number should be among the values of StreamingFeature

Config for STREAMING_SHOT_CHANGE_DETECTION.

This object should have the same structure as StreamingShotChangeDetectionConfig

Config for STREAMING_LABEL_DETECTION.

This object should have the same structure as StreamingLabelDetectionConfig

Config for STREAMING_EXPLICIT_CONTENT_DETECTION.

This object should have the same structure as StreamingExplicitContentDetectionConfig

Config for STREAMING_OBJECT_TRACKING.

This object should have the same structure as StreamingObjectTrackingConfig

Config for STREAMING_AUTOML_CLASSIFICATION.

This object should have the same structure as StreamingAutomlClassificationConfig

Config for STREAMING_AUTOML_OBJECT_TRACKING.

This object should have the same structure as StreamingAutomlObjectTrackingConfig

Streaming storage option. By default: storage is disabled.

This object should have the same structure as StreamingStorageConfig

The detected text.

All video segments where OCR detected text appears.

This object should have the same structure as TextSegment

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.

Model to use for text detection. Supported values: "builtin/stable" (the default if unset) and "builtin/latest".

Bounding polygon of the detected text for this frame.

This object should have the same structure as NormalizedBoundingPoly

Timestamp of this frame.

This object should have the same structure as Duration

Video segment where a text snippet was detected.

This object should have the same structure as VideoSegment

Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears.

Information related to the frames where OCR detected text appears.

This object should have the same structure as TextFrame

Normalized Bounding box in a frame, where the object is located.

This object should have the same structure as NormalizedBoundingBox

Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.

This object should have the same structure as Duration

Optional. The attributes of the object in the bounding box.

This object should have the same structure as DetectedAttribute

Video segment of a track.

This object should have the same structure as VideoSegment

The object with timestamp and attributes per frame in the track.

This object should have the same structure as TimestampedObject

Optional. Attributes in the track level.

This object should have the same structure as DetectedAttribute

Optional. The confidence score of the tracked object.

Video file location in Google Cloud Storage.

Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.

Time when the request was received.

This object should have the same structure as Timestamp

Time of the most recent update.

This object should have the same structure as Timestamp

Video file location in Google Cloud Storage.

Label annotations on video level or user specified segment level. There is exactly one element for each unique label.

This object should have the same structure as LabelAnnotation

Label annotations on shot level. There is exactly one element for each unique label.

This object should have the same structure as LabelAnnotation

Label annotations on frame level. There is exactly one element for each unique label.

This object should have the same structure as LabelAnnotation

Shot annotations. Each shot is represented as a video segment.

This object should have the same structure as VideoSegment

Explicit content annotation.

This object should have the same structure as ExplicitContentAnnotation

Speech transcription.

This object should have the same structure as SpeechTranscription

OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it.

This object should have the same structure as TextAnnotation

Annotations for list of objects detected and tracked in video.

This object should have the same structure as ObjectTrackingAnnotation

Annotations for list of logos detected, tracked and recognized in video.

This object should have the same structure as LogoRecognitionAnnotation

If set, indicates an error. Note that for a single AnnotateVideoRequest some videos may succeed and some may fail.

This object should have the same structure as Status

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.

This object should have the same structure as VideoSegment

Config for LABEL_DETECTION.

This object should have the same structure as LabelDetectionConfig

Config for SHOT_CHANGE_DETECTION.

This object should have the same structure as ShotChangeDetectionConfig

Config for EXPLICIT_CONTENT_DETECTION.

This object should have the same structure as ExplicitContentDetectionConfig

Config for SPEECH_TRANSCRIPTION.

This object should have the same structure as SpeechTranscriptionConfig

Config for TEXT_DETECTION.

This object should have the same structure as TextDetectionConfig

Config for OBJECT_TRACKING.

This object should have the same structure as ObjectTrackingConfig

Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive).

This object should have the same structure as Duration

Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).

This object should have the same structure as Duration

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.

This object should have the same structure as Duration

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.

This object should have the same structure as Duration

The word corresponding to this set of information.

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.

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.