openapi-directory
Version:
Building & bundling https://github.com/APIs-guru/openapi-directory for easy use from JS
1 lines • 155 kB
JSON
{"openapi":"3.0.0","servers":[{"url":"https://videointelligence.googleapis.com/"}],"info":{"contact":{"name":"Google","url":"https://google.com","x-twitter":"youtube"},"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.","license":{"name":"Creative Commons Attribution 3.0","url":"http://creativecommons.org/licenses/by/3.0/"},"termsOfService":"https://developers.google.com/terms/","title":"Cloud Video Intelligence API","version":"v1p3beta1","x-apiClientRegistration":{"url":"https://console.developers.google.com"},"x-apisguru-categories":["analytics","media"],"x-logo":{"url":"https://www.google.com/images/branding/googlelogo/2x/googlelogo_color_272x92dp.png"},"x-origin":[{"format":"google","url":"https://videointelligence.googleapis.com/$discovery/rest?version=v1p3beta1","version":"v1"}],"x-preferred":true,"x-providerName":"googleapis.com","x-serviceName":"videointelligence"},"externalDocs":{"url":"https://cloud.google.com/video-intelligence/docs/"},"tags":[{"name":"videos"}],"paths":{"/v1p3beta1/videos:annotate":{"parameters":[{"$ref":"#/components/parameters/_.xgafv"},{"$ref":"#/components/parameters/access_token"},{"$ref":"#/components/parameters/alt"},{"$ref":"#/components/parameters/callback"},{"$ref":"#/components/parameters/fields"},{"$ref":"#/components/parameters/key"},{"$ref":"#/components/parameters/oauth_token"},{"$ref":"#/components/parameters/prettyPrint"},{"$ref":"#/components/parameters/quotaUser"},{"$ref":"#/components/parameters/upload_protocol"},{"$ref":"#/components/parameters/uploadType"}],"post":{"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).","operationId":"videointelligence.videos.annotate","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoRequest"}}}},"responses":{"200":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/GoogleLongrunning_Operation"}}},"description":"Successful response"}},"security":[{"Oauth2":["https://www.googleapis.com/auth/cloud-platform"],"Oauth2c":["https://www.googleapis.com/auth/cloud-platform"]}],"tags":["videos"]}}},"components":{"parameters":{"_.xgafv":{"description":"V1 error format.","in":"query","name":"$.xgafv","schema":{"enum":["1","2"],"type":"string"}},"access_token":{"description":"OAuth access token.","in":"query","name":"access_token","schema":{"type":"string"}},"alt":{"description":"Data format for response.","in":"query","name":"alt","schema":{"enum":["json","media","proto"],"type":"string"}},"callback":{"description":"JSONP","in":"query","name":"callback","schema":{"type":"string"}},"fields":{"description":"Selector specifying which fields to include in a partial response.","in":"query","name":"fields","schema":{"type":"string"}},"key":{"description":"API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.","in":"query","name":"key","schema":{"type":"string"}},"oauth_token":{"description":"OAuth 2.0 token for the current user.","in":"query","name":"oauth_token","schema":{"type":"string"}},"prettyPrint":{"description":"Returns response with indentations and line breaks.","in":"query","name":"prettyPrint","schema":{"type":"boolean"}},"quotaUser":{"description":"Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.","in":"query","name":"quotaUser","schema":{"type":"string"}},"uploadType":{"description":"Legacy upload protocol for media (e.g. \"media\", \"multipart\").","in":"query","name":"uploadType","schema":{"type":"string"}},"upload_protocol":{"description":"Upload protocol for media (e.g. \"raw\", \"multipart\").","in":"query","name":"upload_protocol","schema":{"type":"string"}}},"schemas":{"GoogleCloudVideointelligenceV1_AnnotateVideoProgress":{"description":"Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.","properties":{"annotationProgress":{"description":"Progress metadata for all videos specified in `AnnotateVideoRequest`.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_VideoAnnotationProgress"},"type":"array"}},"type":"object"},"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.","properties":{"annotationResults":{"description":"Annotation results for all videos specified in `AnnotateVideoRequest`.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_VideoAnnotationResults"},"type":"array"}},"type":"object"},"GoogleCloudVideointelligenceV1_DetectedAttribute":{"description":"A generic detected attribute represented by name in string format.","properties":{"confidence":{"description":"Detected attribute confidence. Range [0, 1].","format":"float","type":"number"},"name":{"description":"The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document.","type":"string"},"value":{"description":"Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc.","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1_DetectedLandmark":{"description":"A generic detected landmark represented by name in string format and a 2D location.","properties":{"confidence":{"description":"The confidence score of the detected landmark. Range [0, 1].","format":"float","type":"number"},"name":{"description":"The name of this landmark, for example, left_hand, right_shoulder.","type":"string"},"point":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_NormalizedVertex","description":"The 2D point of the detected landmark using the normalized image coordindate system. The normalized coordinates have the range from 0 to 1."}},"type":"object"},"GoogleCloudVideointelligenceV1_Entity":{"description":"Detected entity from video analysis.","properties":{"description":{"description":"Textual description, e.g., `Fixed-gear bicycle`.","type":"string"},"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"}},"type":"object"},"GoogleCloudVideointelligenceV1_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.","properties":{"frames":{"description":"All video frames where explicit content was detected.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_ExplicitContentFrame"},"type":"array"},"version":{"description":"Feature version.","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1_ExplicitContentFrame":{"description":"Video frame level annotation results for explicit content.","properties":{"pornographyLikelihood":{"description":"Likelihood of the pornography content..","enum":["LIKELIHOOD_UNSPECIFIED","VERY_UNLIKELY","UNLIKELY","POSSIBLE","LIKELY","VERY_LIKELY"],"type":"string"},"timeOffset":{"description":"Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.","format":"google-duration","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1_FaceAnnotation":{"deprecated":true,"description":"Deprecated. No effect.","properties":{"frames":{"description":"All video frames where a face was detected.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_FaceFrame"},"type":"array"},"segments":{"description":"All video segments where a face was detected.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_FaceSegment"},"type":"array"},"thumbnail":{"description":"Thumbnail of a representative face view (in JPEG format).","format":"byte","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1_FaceDetectionAnnotation":{"description":"Face detection annotation.","properties":{"thumbnail":{"description":"The thumbnail of a person's face.","format":"byte","type":"string"},"tracks":{"description":"The face tracks with attributes.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_Track"},"type":"array"},"version":{"description":"Feature version.","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1_FaceFrame":{"deprecated":true,"description":"Deprecated. No effect.","properties":{"normalizedBoundingBoxes":{"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":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_NormalizedBoundingBox"},"type":"array"},"timeOffset":{"description":"Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.","format":"google-duration","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1_FaceSegment":{"description":"Video segment level annotation results for face detection.","properties":{"segment":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_VideoSegment","description":"Video segment where a face was detected."}},"type":"object"},"GoogleCloudVideointelligenceV1_LabelAnnotation":{"description":"Label annotation.","properties":{"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":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_Entity"},"type":"array"},"entity":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_Entity","description":"Detected entity."},"frames":{"description":"All video frames where a label was detected.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_LabelFrame"},"type":"array"},"segments":{"description":"All video segments where a label was detected.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_LabelSegment"},"type":"array"},"version":{"description":"Feature version.","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1_LabelFrame":{"description":"Video frame level annotation results for label detection.","properties":{"confidence":{"description":"Confidence that the label is accurate. Range: [0, 1].","format":"float","type":"number"},"timeOffset":{"description":"Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.","format":"google-duration","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1_LabelSegment":{"description":"Video segment level annotation results for label detection.","properties":{"confidence":{"description":"Confidence that the label is accurate. Range: [0, 1].","format":"float","type":"number"},"segment":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_VideoSegment","description":"Video segment where a label was detected."}},"type":"object"},"GoogleCloudVideointelligenceV1_LogoRecognitionAnnotation":{"description":"Annotation corresponding to one detected, tracked and recognized logo class.","properties":{"entity":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_Entity","description":"Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as."},"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":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_VideoSegment"},"type":"array"},"tracks":{"description":"All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_Track"},"type":"array"}},"type":"object"},"GoogleCloudVideointelligenceV1_NormalizedBoundingBox":{"description":"Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1].","properties":{"bottom":{"description":"Bottom Y coordinate.","format":"float","type":"number"},"left":{"description":"Left X coordinate.","format":"float","type":"number"},"right":{"description":"Right X coordinate.","format":"float","type":"number"},"top":{"description":"Top Y coordinate.","format":"float","type":"number"}},"type":"object"},"GoogleCloudVideointelligenceV1_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 trignometric calculations for location of the box.","properties":{"vertices":{"description":"Normalized vertices of the bounding polygon.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_NormalizedVertex"},"type":"array"}},"type":"object"},"GoogleCloudVideointelligenceV1_NormalizedVertex":{"description":"A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.","properties":{"x":{"description":"X coordinate.","format":"float","type":"number"},"y":{"description":"Y coordinate.","format":"float","type":"number"}},"type":"object"},"GoogleCloudVideointelligenceV1_ObjectTrackingAnnotation":{"description":"Annotations corresponding to one tracked object.","properties":{"confidence":{"description":"Object category's labeling confidence of this track.","format":"float","type":"number"},"entity":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_Entity","description":"Entity to specify the object category that this track is labeled as."},"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":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_ObjectTrackingFrame"},"type":"array"},"segment":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_VideoSegment","description":"Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears."},"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"},"version":{"description":"Feature version.","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1_ObjectTrackingFrame":{"description":"Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence.","properties":{"normalizedBoundingBox":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_NormalizedBoundingBox","description":"The normalized bounding box location of this object track for the frame."},"timeOffset":{"description":"The timestamp of the frame in microseconds.","format":"google-duration","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1_PersonDetectionAnnotation":{"description":"Person detection annotation per video.","properties":{"tracks":{"description":"The detected tracks of a person.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_Track"},"type":"array"},"version":{"description":"Feature version.","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1_SpeechRecognitionAlternative":{"description":"Alternative hypotheses (a.k.a. n-best list).","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":{"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.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_WordInfo"},"readOnly":true,"type":"array"}},"type":"object"},"GoogleCloudVideointelligenceV1_SpeechTranscription":{"description":"A speech recognition result corresponding to a portion of the audio.","properties":{"alternatives":{"description":"May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_SpeechRecognitionAlternative"},"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"}},"type":"object"},"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.","properties":{"segments":{"description":"All video segments where OCR detected text appears.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_TextSegment"},"type":"array"},"text":{"description":"The detected text.","type":"string"},"version":{"description":"Feature version.","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1_TextFrame":{"description":"Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.","properties":{"rotatedBoundingBox":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_NormalizedBoundingPoly","description":"Bounding polygon of the detected text for this frame."},"timeOffset":{"description":"Timestamp of this frame.","format":"google-duration","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1_TextSegment":{"description":"Video segment level annotation results for text detection.","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":{"description":"Information related to the frames where OCR detected text appears.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_TextFrame"},"type":"array"},"segment":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_VideoSegment","description":"Video segment where a text snippet was detected."}},"type":"object"},"GoogleCloudVideointelligenceV1_TimestampedObject":{"description":"For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box.","properties":{"attributes":{"description":"Optional. The attributes of the object in the bounding box.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_DetectedAttribute"},"type":"array"},"landmarks":{"description":"Optional. The detected landmarks.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_DetectedLandmark"},"type":"array"},"normalizedBoundingBox":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_NormalizedBoundingBox","description":"Normalized Bounding box in a frame, where the object is located."},"timeOffset":{"description":"Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.","format":"google-duration","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1_Track":{"description":"A track of an object instance.","properties":{"attributes":{"description":"Optional. Attributes in the track level.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_DetectedAttribute"},"type":"array"},"confidence":{"description":"Optional. The confidence score of the tracked object.","format":"float","type":"number"},"segment":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_VideoSegment","description":"Video segment of a track."},"timestampedObjects":{"description":"The object with timestamp and attributes per frame in the track.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_TimestampedObject"},"type":"array"}},"type":"object"},"GoogleCloudVideointelligenceV1_VideoAnnotationProgress":{"description":"Annotation progress for a single video.","properties":{"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"],"type":"string"},"inputUri":{"description":"Video file location in [Cloud Storage](https://cloud.google.com/storage/).","type":"string"},"progressPercent":{"description":"Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.","format":"int32","type":"integer"},"segment":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_VideoSegment","description":"Specifies which segment is being tracked if the request contains more than one segment."},"startTime":{"description":"Time when the request was received.","format":"google-datetime","type":"string"},"updateTime":{"description":"Time of the most recent update.","format":"google-datetime","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1_VideoAnnotationResults":{"description":"Annotation results for a single video.","properties":{"error":{"$ref":"#/components/schemas/GoogleRpc_Status","description":"If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail."},"explicitAnnotation":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_ExplicitContentAnnotation","description":"Explicit content annotation."},"faceAnnotations":{"deprecated":true,"description":"Deprecated. Please use `face_detection_annotations` instead.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_FaceAnnotation"},"type":"array"},"faceDetectionAnnotations":{"description":"Face detection annotations.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_FaceDetectionAnnotation"},"type":"array"},"frameLabelAnnotations":{"description":"Label annotations on frame level. There is exactly one element for each unique label.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_LabelAnnotation"},"type":"array"},"inputUri":{"description":"Video file location in [Cloud Storage](https://cloud.google.com/storage/).","type":"string"},"logoRecognitionAnnotations":{"description":"Annotations for list of logos detected, tracked and recognized in video.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_LogoRecognitionAnnotation"},"type":"array"},"objectAnnotations":{"description":"Annotations for list of objects detected and tracked in video.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_ObjectTrackingAnnotation"},"type":"array"},"personDetectionAnnotations":{"description":"Person detection annotations.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_PersonDetectionAnnotation"},"type":"array"},"segment":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_VideoSegment","description":"Video segment on which the annotation is run."},"segmentLabelAnnotations":{"description":"Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_LabelAnnotation"},"type":"array"},"segmentPresenceLabelAnnotations":{"description":"Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_LabelAnnotation"},"type":"array"},"shotAnnotations":{"description":"Shot annotations. Each shot is represented as a video segment.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_VideoSegment"},"type":"array"},"shotLabelAnnotations":{"description":"Topical label annotations on shot level. There is exactly one element for each unique label.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_LabelAnnotation"},"type":"array"},"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":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_LabelAnnotation"},"type":"array"},"speechTranscriptions":{"description":"Speech transcription.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1_SpeechTranscription"},"type":"array"},"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":"#/components/schemas/GoogleCloudVideointelligenceV1_TextAnnotation"},"type":"array"}},"type":"object"},"GoogleCloudVideointelligenceV1_VideoSegment":{"description":"Video segment.","properties":{"endTimeOffset":{"description":"Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).","format":"google-duration","type":"string"},"startTimeOffset":{"description":"Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive).","format":"google-duration","type":"string"}},"type":"object"},"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`.","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":{"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"},"speakerTag":{"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,"type":"integer"},"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"},"word":{"description":"The word corresponding to this set of information.","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_AnnotateVideoProgress":{"description":"Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.","properties":{"annotationProgress":{"description":"Progress metadata for all videos specified in `AnnotateVideoRequest`.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_VideoAnnotationProgress"},"type":"array"}},"type":"object"},"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.","properties":{"annotationResults":{"description":"Annotation results for all videos specified in `AnnotateVideoRequest`.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_VideoAnnotationResults"},"type":"array"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_DetectedAttribute":{"description":"A generic detected attribute represented by name in string format.","properties":{"confidence":{"description":"Detected attribute confidence. Range [0, 1].","format":"float","type":"number"},"name":{"description":"The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document.","type":"string"},"value":{"description":"Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc.","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_DetectedLandmark":{"description":"A generic detected landmark represented by name in string format and a 2D location.","properties":{"confidence":{"description":"The confidence score of the detected landmark. Range [0, 1].","format":"float","type":"number"},"name":{"description":"The name of this landmark, for example, left_hand, right_shoulder.","type":"string"},"point":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_NormalizedVertex","description":"The 2D point of the detected landmark using the normalized image coordindate system. The normalized coordinates have the range from 0 to 1."}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_Entity":{"description":"Detected entity from video analysis.","properties":{"description":{"description":"Textual description, e.g., `Fixed-gear bicycle`.","type":"string"},"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"}},"type":"object"},"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.","properties":{"frames":{"description":"All video frames where explicit content was detected.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_ExplicitContentFrame"},"type":"array"},"version":{"description":"Feature version.","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_ExplicitContentFrame":{"description":"Video frame level annotation results for explicit content.","properties":{"pornographyLikelihood":{"description":"Likelihood of the pornography content..","enum":["LIKELIHOOD_UNSPECIFIED","VERY_UNLIKELY","UNLIKELY","POSSIBLE","LIKELY","VERY_LIKELY"],"type":"string"},"timeOffset":{"description":"Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.","format":"google-duration","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_FaceAnnotation":{"deprecated":true,"description":"Deprecated. No effect.","properties":{"frames":{"description":"All video frames where a face was detected.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_FaceFrame"},"type":"array"},"segments":{"description":"All video segments where a face was detected.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_FaceSegment"},"type":"array"},"thumbnail":{"description":"Thumbnail of a representative face view (in JPEG format).","format":"byte","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_FaceDetectionAnnotation":{"description":"Face detection annotation.","properties":{"thumbnail":{"description":"The thumbnail of a person's face.","format":"byte","type":"string"},"tracks":{"description":"The face tracks with attributes.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_Track"},"type":"array"},"version":{"description":"Feature version.","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_FaceFrame":{"deprecated":true,"description":"Deprecated. No effect.","properties":{"normalizedBoundingBoxes":{"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":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox"},"type":"array"},"timeOffset":{"description":"Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.","format":"google-duration","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_FaceSegment":{"description":"Video segment level annotation results for face detection.","properties":{"segment":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_VideoSegment","description":"Video segment where a face was detected."}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_LabelAnnotation":{"description":"Label annotation.","properties":{"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":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_Entity"},"type":"array"},"entity":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_Entity","description":"Detected entity."},"frames":{"description":"All video frames where a label was detected.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_LabelFrame"},"type":"array"},"segments":{"description":"All video segments where a label was detected.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_LabelSegment"},"type":"array"},"version":{"description":"Feature version.","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_LabelFrame":{"description":"Video frame level annotation results for label detection.","properties":{"confidence":{"description":"Confidence that the label is accurate. Range: [0, 1].","format":"float","type":"number"},"timeOffset":{"description":"Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.","format":"google-duration","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_LabelSegment":{"description":"Video segment level annotation results for label detection.","properties":{"confidence":{"description":"Confidence that the label is accurate. Range: [0, 1].","format":"float","type":"number"},"segment":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_VideoSegment","description":"Video segment where a label was detected."}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_LogoRecognitionAnnotation":{"description":"Annotation corresponding to one detected, tracked and recognized logo class.","properties":{"entity":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_Entity","description":"Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as."},"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":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_VideoSegment"},"type":"array"},"tracks":{"description":"All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_Track"},"type":"array"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox":{"description":"Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1].","properties":{"bottom":{"description":"Bottom Y coordinate.","format":"float","type":"number"},"left":{"description":"Left X coordinate.","format":"float","type":"number"},"right":{"description":"Right X coordinate.","format":"float","type":"number"},"top":{"description":"Top Y coordinate.","format":"float","type":"number"}},"type":"object"},"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 trignometric calculations for location of the box.","properties":{"vertices":{"description":"Normalized vertices of the bounding polygon.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_NormalizedVertex"},"type":"array"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_NormalizedVertex":{"description":"A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.","properties":{"x":{"description":"X coordinate.","format":"float","type":"number"},"y":{"description":"Y coordinate.","format":"float","type":"number"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_ObjectTrackingAnnotation":{"description":"Annotations corresponding to one tracked object.","properties":{"confidence":{"description":"Object category's labeling confidence of this track.","format":"float","type":"number"},"entity":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_Entity","description":"Entity to specify the object category that this track is labeled as."},"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":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_ObjectTrackingFrame"},"type":"array"},"segment":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_VideoSegment","description":"Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears."},"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"},"version":{"description":"Feature version.","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_ObjectTrackingFrame":{"description":"Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence.","properties":{"normalizedBoundingBox":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox","description":"The normalized bounding box location of this object track for the frame."},"timeOffset":{"description":"The timestamp of the frame in microseconds.","format":"google-duration","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_PersonDetectionAnnotation":{"description":"Person detection annotation per video.","properties":{"tracks":{"description":"The detected tracks of a person.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_Track"},"type":"array"},"version":{"description":"Feature version.","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_SpeechRecognitionAlternative":{"description":"Alternative hypotheses (a.k.a. n-best list).","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":{"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.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_WordInfo"},"readOnly":true,"type":"array"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_SpeechTranscription":{"description":"A speech recognition result corresponding to a portion of the audio.","properties":{"alternatives":{"description":"May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_SpeechRecognitionAlternative"},"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"}},"type":"object"},"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.","properties":{"segments":{"description":"All video segments where OCR detected text appears.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_TextSegment"},"type":"array"},"text":{"description":"The detected text.","type":"string"},"version":{"description":"Feature version.","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_TextFrame":{"description":"Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.","properties":{"rotatedBoundingBox":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_NormalizedBoundingPoly","description":"Bounding polygon of the detected text for this frame."},"timeOffset":{"description":"Timestamp of this frame.","format":"google-duration","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_TextSegment":{"description":"Video segment level annotation results for text detection.","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":{"description":"Information related to the frames where OCR detected text appears.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_TextFrame"},"type":"array"},"segment":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_VideoSegment","description":"Video segment where a text snippet was detected."}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_TimestampedObject":{"description":"For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box.","properties":{"attributes":{"description":"Optional. The attributes of the object in the bounding box.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_DetectedAttribute"},"type":"array"},"landmarks":{"description":"Optional. The detected landmarks.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_DetectedLandmark"},"type":"array"},"normalizedBoundingBox":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox","description":"Normalized Bounding box in a frame, where the object is located."},"timeOffset":{"description":"Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.","format":"google-duration","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_Track":{"description":"A track of an object instance.","properties":{"attributes":{"description":"Optional. Attributes in the track level.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_DetectedAttribute"},"type":"array"},"confidence":{"description":"Optional. The confidence score of the tracked object.","format":"float","type":"number"},"segment":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_VideoSegment","description":"Video segment of a track."},"timestampedObjects":{"description":"The object with timestamp and attributes per frame in the track.","items":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_TimestampedObject"},"type":"array"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_VideoAnnotationProgress":{"description":"Annotation progress for a single video.","properties":{"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"],"type":"string"},"inputUri":{"description":"Video file location in [Cloud Storage](https://cloud.google.com/storage/).","type":"string"},"progressPercent":{"description":"Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.","format":"int32","type":"integer"},"segment":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_VideoSegment","description":"Specifies which segment is being tracked if the request contains more than one segment."},"startTime":{"description":"Time when the request was received.","format":"google-datetime","type":"string"},"updateTime":{"description":"Time of the most recent update.","format":"google-datetime","type":"string"}},"type":"object"},"GoogleCloudVideointelligenceV1beta2_VideoAnnotationResults":{"description":"Annotation results for a single video.","properties":{"error":{"$ref":"#/components/schemas/GoogleRpc_Status","description":"If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail."},"explicitAnnotation":{"$ref":"#/components/schemas/GoogleCloudVideointelligenceV1beta2_ExplicitContentAnnotation","description":"Explicit content annotation."},"faceAnnotations":{"deprecated":true,"description":"Deprecated. Please use `face_detection_annotations