Every API here is available over the APIs.io API and to AI agents over MCP.
openapi: 3.2.0
info:
title: Cloud Video Intelligence Videos API
version: v1
description: Generated from Google's published Discovery document for Cloud Video Intelligence API (videointelligence v1, revision 20261106). 1 operation(s).
contact:
name: Google
url: https://developers.google.com/
termsOfService: https://developers.google.com/terms
servers:
- url: https://videointelligence.googleapis.com
tags:
- name: Videos
paths:
/v1/videos:annotate:
post:
operationId: videointelligence.videos.annotate
summary: Annotate videos
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).
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/GoogleCloudVideointelligenceV1_AnnotateVideoRequest'
responses:
'200':
description: Successful response
content:
application/json:
schema:
$ref: '#/components/schemas/GoogleLongrunning_Operation'
4XX:
content:
application/json:
schema:
$ref: '#/components/schemas/GoogleRpcError'
description: 'Client error (google.rpc.Status: INVALID_ARGUMENT, PERMISSION_DENIED, NOT_FOUND ...)'
default:
content:
application/json:
schema:
$ref: '#/components/schemas/GoogleRpcError'
description: Error response (google.rpc.Status)
security:
- oauth2:
- https://www.googleapis.com/auth/cloud-platform
- apiKey: []
tags:
- Videos
components:
schemas:
GoogleCloudVideointelligenceV1_TextDetectionConfig:
properties:
languageHints:
type: array
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
model:
type: string
description: 'Model to use for text detection. Supported values: "builtin/stable" (the default if unset) and "builtin/latest".'
description: Config for TEXT_DETECTION.
type: object
GoogleCloudVideointelligenceV1_SpeechTranscriptionConfig:
properties:
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.
audioTracks:
items:
type: integer
format: int32
type: array
description: 'Optional. For file formats, such as MXF or MKV, supporting multiple audio tracks, specify up to two tracks. Default: track 0.'
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."'
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
audioOutputUriPrefix:
type: string
description: Optional. Legacy field. This field must be a Cloud Storage URI prefix. (e.g., `gs://bucket/path/`).
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
speechContexts:
type: array
items:
$ref: '#/components/schemas/GoogleCloudVideointelligenceV1_SpeechContext'
description: Optional. A means to provide context to assist the speech recognition.
diarizationSpeakerCount:
type: integer
format: int32
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.
maxAlternatives:
format: int32
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.
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
description: Config for SPEECH_TRANSCRIPTION.
type: object
GoogleCloudVideointelligenceV1_LabelDetectionConfig:
description: Config for LABEL_DETECTION.
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
frameConfidenceThreshold:
format: float
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.'
type: number
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
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
GoogleRpcError:
type: object
description: The error envelope every Google API returns.
properties:
error:
type: object
properties:
code:
type: integer
message:
type: string
status:
type: string
details:
type: array
items:
type: object
GoogleCloudVideointelligenceV1_ObjectTrackingConfig:
type: object
description: Config for OBJECT_TRACKING.
properties:
model:
type: string
description: 'Model to use for object tracking. Supported values: "builtin/stable" (the default if unset) and "builtin/latest".'
GoogleCloudVideointelligenceV1_ExplicitContentDetectionConfig:
properties:
model:
description: 'Model to use for explicit content detection. Supported values: "builtin/stable" (the default if unset) and "builtin/latest".'
type: string
description: Config for EXPLICIT_CONTENT_DETECTION.
type: object
GoogleLongrunning_Operation:
description: This resource represents a long-running operation that is the result of a network API call.
properties:
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:
$ref: '#/components/schemas/GoogleRpc_Status'
description: The error result of the operation in case of failure or cancellation.
metadata:
type: object
additionalProperties:
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.
response:
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: object
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.
type: object
GoogleCloudVideointelligenceV1_FaceDetectionConfig:
type: object
properties:
model:
type: string
description: 'Model to use for face detection. Supported values: "builtin/stable" (the default if unset) and "builtin/latest".'
includeAttributes:
type: boolean
description: Whether to enable face attributes detection, such as glasses, dark_glasses, mouth_open etc. Ignored if 'include_bounding_boxes' is set to false.
includeBoundingBoxes:
description: Whether bounding boxes are included in the face annotation output.
type: boolean
description: Config for FACE_DETECTION.
GoogleCloudVideointelligenceV1_PersonDetectionConfig:
properties:
includeBoundingBoxes:
description: Whether bounding boxes are included in the person detection annotation output.
type: boolean
includeAttributes:
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.
type: boolean
includePoseLandmarks:
description: Whether to enable pose landmarks detection. Ignored if 'include_bounding_boxes' is set to false.
type: boolean
type: object
description: Config for PERSON_DETECTION.
GoogleRpc_Status:
type: object
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).'
properties:
code:
type: integer
format: int32
description: The status code, which should be an enum value of google.rpc.Code.
message:
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.
type: string
details:
type: array
description: A list of messages that carry the error details. There is a common set of message types for APIs to use.
items:
additionalProperties:
description: Properties of the object. Contains field @type with type URL.
type: object
GoogleCloudVideointelligenceV1_AnnotateVideoRequest:
description: Video annotation request.
type: object
properties:
inputUri:
type: string
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.'
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
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
videoContext:
$ref: '#/components/schemas/GoogleCloudVideointelligenceV1_VideoContext'
description: Additional video context and/or feature-specific parameters.
features:
description: Required. Requested video annotation features.
type: array
items:
type: string
enum:
- FEATURE_UNSPECIFIED
- LABEL_DETECTION
- SHOT_CHANGE_DETECTION
- EXPLICIT_CONTENT_DETECTION
- FACE_DETECTION
- SPEECH_TRANSCRIPTION
- TEXT_DETECTION
- OBJECT_TRACKING
- LOGO_RECOGNITION
- PERSON_DETECTION
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
GoogleCloudVideointelligenceV1_VideoSegment:
type: object
properties:
endTimeOffset:
type: string
description: Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).
format: google-duration
startTimeOffset:
description: Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive).
type: string
format: google-duration
description: Video segment.
GoogleCloudVideointelligenceV1_VideoContext:
description: Video context and/or feature-specific parameters.
properties:
speechTranscriptionConfig:
$ref: '#/components/schemas/GoogleCloudVideointelligenceV1_SpeechTranscriptionConfig'
description: Config for SPEECH_TRANSCRIPTION.
faceDetectionConfig:
$ref: '#/components/schemas/GoogleCloudVideointelligenceV1_FaceDetectionConfig'
description: Config for FACE_DETECTION.
textDetectionConfig:
$ref: '#/components/schemas/GoogleCloudVideointelligenceV1_TextDetectionConfig'
description: Config for TEXT_DETECTION.
shotChangeDetectionConfig:
$ref: '#/components/schemas/GoogleCloudVideointelligenceV1_ShotChangeDetectionConfig'
description: Config for SHOT_CHANGE_DETECTION.
objectTrackingConfig:
$ref: '#/components/schemas/GoogleCloudVideointelligenceV1_ObjectTrackingConfig'
description: Config for OBJECT_TRACKING.
labelDetectionConfig:
$ref: '#/components/schemas/GoogleCloudVideointelligenceV1_LabelDetectionConfig'
description: Config for LABEL_DETECTION.
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: '#/components/schemas/GoogleCloudVideointelligenceV1_VideoSegment'
type: array
personDetectionConfig:
$ref: '#/components/schemas/GoogleCloudVideointelligenceV1_PersonDetectionConfig'
description: Config for PERSON_DETECTION.
explicitContentDetectionConfig:
$ref: '#/components/schemas/GoogleCloudVideointelligenceV1_ExplicitContentDetectionConfig'
description: Config for EXPLICIT_CONTENT_DETECTION.
type: object
GoogleCloudVideointelligenceV1_SpeechContext:
properties:
phrases:
type: array
items:
type: string
description: Optional. A list of strings containing words and phrases "hints" so that the speech recognition is more likely to recognize them. This can be used to improve the accuracy for specific words and phrases, for example, if specific commands are typically spoken by the user. This can also be used to add additional words to the vocabulary of the recognizer. See [usage limits](https://cloud.google.com/speech/limits#content).
type: object
description: Provides "hints" to the speech recognizer to favor specific words and phrases in the results.
GoogleCloudVideointelligenceV1_ShotChangeDetectionConfig:
properties:
model:
description: 'Model to use for shot change detection. Supported values: "builtin/stable" (the default if unset), "builtin/latest", and "builtin/legacy".'
type: string
type: object
description: Config for SHOT_CHANGE_DETECTION.
securitySchemes:
apiKey:
type: apiKey
in: query
name: key
description: API key; accepted by methods that do not need user data.
oauth2:
type: oauth2
flows:
authorizationCode:
authorizationUrl: https://accounts.google.com/o/oauth2/auth
tokenUrl: https://oauth2.googleapis.com/token
scopes:
https://www.googleapis.com/auth/cloud-platform: See, edit, configure, and delete your Google Cloud data and see the email address for your Google Account.
externalDocs:
url: https://cloud.google.com/video-intelligence/docs/
x-provenance:
method: harvested
publisher: Google
source: https://videointelligence.googleapis.com/$discovery/rest?version=v1
note: converted by discovery-to-openapi.py from Google's Discovery document (revision 20261106)