blob: da3cca7f74514620aa9377f79e62bfd7d8e61c92 [file] [log] [blame]
{
"auth": {
"oauth2": {
"scopes": {
"https://www.googleapis.com/auth/cloud-platform": {
"description": "View and manage your data across Google Cloud Platform services"
}
}
}
},
"basePath": "",
"baseUrl": "https://videointelligence.googleapis.com/",
"batchPath": "batch",
"canonicalName": "Cloud Video Intelligence",
"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",
"documentationLink": "https://cloud.google.com/video-intelligence/docs/",
"fullyEncodeReservedExpansion": true,
"icons": {
"x16": "http://www.google.com/images/icons/product/search-16.gif",
"x32": "http://www.google.com/images/icons/product/search-32.gif"
},
"id": "videointelligence:v1",
"kind": "discovery#restDescription",
"mtlsRootUrl": "https://videointelligence.mtls.googleapis.com/",
"name": "videointelligence",
"ownerDomain": "google.com",
"ownerName": "Google",
"parameters": {
"$.xgafv": {
"description": "V1 error format.",
"enum": [
"1",
"2"
],
"enumDescriptions": [
"v1 error format",
"v2 error format"
],
"location": "query",
"type": "string"
},
"access_token": {
"description": "OAuth access token.",
"location": "query",
"type": "string"
},
"alt": {
"default": "json",
"description": "Data format for response.",
"enum": [
"json",
"media",
"proto"
],
"enumDescriptions": [
"Responses with Content-Type of application/json",
"Media download with context-dependent Content-Type",
"Responses with Content-Type of application/x-protobuf"
],
"location": "query",
"type": "string"
},
"callback": {
"description": "JSONP",
"location": "query",
"type": "string"
},
"fields": {
"description": "Selector specifying which fields to include in a partial response.",
"location": "query",
"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.",
"location": "query",
"type": "string"
},
"oauth_token": {
"description": "OAuth 2.0 token for the current user.",
"location": "query",
"type": "string"
},
"prettyPrint": {
"default": "true",
"description": "Returns response with indentations and line breaks.",
"location": "query",
"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.",
"location": "query",
"type": "string"
},
"uploadType": {
"description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").",
"location": "query",
"type": "string"
},
"upload_protocol": {
"description": "Upload protocol for media (e.g. \"raw\", \"multipart\").",
"location": "query",
"type": "string"
}
},
"protocol": "rest",
"resources": {
"operations": {
"resources": {
"projects": {
"resources": {
"locations": {
"resources": {
"operations": {
"methods": {
"cancel": {
"description": "Starts asynchronous cancellation on a long-running operation. The server\nmakes a best effort to cancel the operation, but success is not\nguaranteed. If the server doesn't support this method, it returns\n`google.rpc.Code.UNIMPLEMENTED`. Clients can use\nOperations.GetOperation or\nother methods to check whether the cancellation succeeded or whether the\noperation completed despite cancellation. On successful cancellation,\nthe operation is not deleted; instead, it becomes an operation with\nan Operation.error value with a google.rpc.Status.code of 1,\ncorresponding to `Code.CANCELLED`.",
"flatPath": "v1/operations/projects/{projectsId}/locations/{locationsId}/operations/{operationsId}:cancel",
"httpMethod": "POST",
"id": "videointelligence.operations.projects.locations.operations.cancel",
"parameterOrder": [
"name"
],
"parameters": {
"name": {
"description": "The name of the operation resource to be cancelled.",
"location": "path",
"pattern": "^projects/[^/]+/locations/[^/]+/operations/[^/]+$",
"required": true,
"type": "string"
}
},
"path": "v1/operations/{+name}:cancel",
"response": {
"$ref": "GoogleProtobuf_Empty"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
},
"delete": {
"description": "Deletes a long-running operation. This method indicates that the client is\nno longer interested in the operation result. It does not cancel the\noperation. If the server doesn't support this method, it returns\n`google.rpc.Code.UNIMPLEMENTED`.",
"flatPath": "v1/operations/projects/{projectsId}/locations/{locationsId}/operations/{operationsId}",
"httpMethod": "DELETE",
"id": "videointelligence.operations.projects.locations.operations.delete",
"parameterOrder": [
"name"
],
"parameters": {
"name": {
"description": "The name of the operation resource to be deleted.",
"location": "path",
"pattern": "^projects/[^/]+/locations/[^/]+/operations/[^/]+$",
"required": true,
"type": "string"
}
},
"path": "v1/operations/{+name}",
"response": {
"$ref": "GoogleProtobuf_Empty"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
},
"get": {
"description": "Gets the latest state of a long-running operation. Clients can use this\nmethod to poll the operation result at intervals as recommended by the API\nservice.",
"flatPath": "v1/operations/projects/{projectsId}/locations/{locationsId}/operations/{operationsId}",
"httpMethod": "GET",
"id": "videointelligence.operations.projects.locations.operations.get",
"parameterOrder": [
"name"
],
"parameters": {
"name": {
"description": "The name of the operation resource.",
"location": "path",
"pattern": "^projects/[^/]+/locations/[^/]+/operations/[^/]+$",
"required": true,
"type": "string"
}
},
"path": "v1/operations/{+name}",
"response": {
"$ref": "GoogleLongrunning_Operation"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
}
}
}
}
}
}
}
}
},
"projects": {
"resources": {
"locations": {
"resources": {
"operations": {
"methods": {
"cancel": {
"description": "Starts asynchronous cancellation on a long-running operation. The server\nmakes a best effort to cancel the operation, but success is not\nguaranteed. If the server doesn't support this method, it returns\n`google.rpc.Code.UNIMPLEMENTED`. Clients can use\nOperations.GetOperation or\nother methods to check whether the cancellation succeeded or whether the\noperation completed despite cancellation. On successful cancellation,\nthe operation is not deleted; instead, it becomes an operation with\nan Operation.error value with a google.rpc.Status.code of 1,\ncorresponding to `Code.CANCELLED`.",
"flatPath": "v1/projects/{projectsId}/locations/{locationsId}/operations/{operationsId}:cancel",
"httpMethod": "POST",
"id": "videointelligence.projects.locations.operations.cancel",
"parameterOrder": [
"name"
],
"parameters": {
"name": {
"description": "The name of the operation resource to be cancelled.",
"location": "path",
"pattern": "^projects/[^/]+/locations/[^/]+/operations/[^/]+$",
"required": true,
"type": "string"
}
},
"path": "v1/{+name}:cancel",
"request": {
"$ref": "GoogleLongrunning_CancelOperationRequest"
},
"response": {
"$ref": "GoogleProtobuf_Empty"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
},
"delete": {
"description": "Deletes a long-running operation. This method indicates that the client is\nno longer interested in the operation result. It does not cancel the\noperation. If the server doesn't support this method, it returns\n`google.rpc.Code.UNIMPLEMENTED`.",
"flatPath": "v1/projects/{projectsId}/locations/{locationsId}/operations/{operationsId}",
"httpMethod": "DELETE",
"id": "videointelligence.projects.locations.operations.delete",
"parameterOrder": [
"name"
],
"parameters": {
"name": {
"description": "The name of the operation resource to be deleted.",
"location": "path",
"pattern": "^projects/[^/]+/locations/[^/]+/operations/[^/]+$",
"required": true,
"type": "string"
}
},
"path": "v1/{+name}",
"response": {
"$ref": "GoogleProtobuf_Empty"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
},
"get": {
"description": "Gets the latest state of a long-running operation. Clients can use this\nmethod to poll the operation result at intervals as recommended by the API\nservice.",
"flatPath": "v1/projects/{projectsId}/locations/{locationsId}/operations/{operationsId}",
"httpMethod": "GET",
"id": "videointelligence.projects.locations.operations.get",
"parameterOrder": [
"name"
],
"parameters": {
"name": {
"description": "The name of the operation resource.",
"location": "path",
"pattern": "^projects/[^/]+/locations/[^/]+/operations/[^/]+$",
"required": true,
"type": "string"
}
},
"path": "v1/{+name}",
"response": {
"$ref": "GoogleLongrunning_Operation"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
},
"list": {
"description": "Lists operations that match the specified filter in the request. If the\nserver doesn't support this method, it returns `UNIMPLEMENTED`.\n\nNOTE: the `name` binding allows API services to override the binding\nto use different resource name schemes, such as `users/*/operations`. To\noverride the binding, API services can add a binding such as\n`\"/v1/{name=users/*}/operations\"` to their service configuration.\nFor backwards compatibility, the default name includes the operations\ncollection id, however overriding users must ensure the name binding\nis the parent resource, without the operations collection id.",
"flatPath": "v1/projects/{projectsId}/locations/{locationsId}/operations",
"httpMethod": "GET",
"id": "videointelligence.projects.locations.operations.list",
"parameterOrder": [
"name"
],
"parameters": {
"filter": {
"description": "The standard list filter.",
"location": "query",
"type": "string"
},
"name": {
"description": "The name of the operation's parent resource.",
"location": "path",
"pattern": "^projects/[^/]+/locations/[^/]+$",
"required": true,
"type": "string"
},
"pageSize": {
"description": "The standard list page size.",
"format": "int32",
"location": "query",
"type": "integer"
},
"pageToken": {
"description": "The standard list page token.",
"location": "query",
"type": "string"
}
},
"path": "v1/{+name}/operations",
"response": {
"$ref": "GoogleLongrunning_ListOperationsResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
}
}
}
}
}
}
},
"videos": {
"methods": {
"annotate": {
"description": "Performs asynchronous video annotation. Progress and results can be\nretrieved through the `google.longrunning.Operations` interface.\n`Operation.metadata` contains `AnnotateVideoProgress` (progress).\n`Operation.response` contains `AnnotateVideoResponse` (results).",
"flatPath": "v1/videos:annotate",
"httpMethod": "POST",
"id": "videointelligence.videos.annotate",
"parameterOrder": [],
"parameters": {},
"path": "v1/videos:annotate",
"request": {
"$ref": "GoogleCloudVideointelligenceV1_AnnotateVideoRequest"
},
"response": {
"$ref": "GoogleLongrunning_Operation"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
}
}
}
},
"revision": "20200226",
"rootUrl": "https://videointelligence.googleapis.com/",
"schemas": {
"GoogleCloudVideointelligenceV1_AnnotateVideoProgress": {
"description": "Video annotation progress. Included in the `metadata`\nfield of the `Operation` returned by the `GetOperation`\ncall of the `google::longrunning::Operations` service.",
"id": "GoogleCloudVideointelligenceV1_AnnotateVideoProgress",
"properties": {
"annotationProgress": {
"description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_VideoAnnotationProgress"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_AnnotateVideoRequest": {
"description": "Video annotation request.",
"id": "GoogleCloudVideointelligenceV1_AnnotateVideoRequest",
"properties": {
"features": {
"description": "Required. Requested video annotation features.",
"enumDescriptions": [
"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."
],
"items": {
"enum": [
"FEATURE_UNSPECIFIED",
"LABEL_DETECTION",
"SHOT_CHANGE_DETECTION",
"EXPLICIT_CONTENT_DETECTION",
"SPEECH_TRANSCRIPTION",
"TEXT_DETECTION",
"OBJECT_TRACKING"
],
"type": "string"
},
"type": "array"
},
"inputContent": {
"description": "The video data bytes.\nIf unset, the input video(s) should be specified via `input_uri`.\nIf set, `input_uri` should be unset.",
"format": "byte",
"type": "string"
},
"inputUri": {
"description": "Input video location. Currently, only\n[Cloud Storage](https://cloud.google.com/storage/) URIs are\nsupported, which must be specified in the following format:\n`gs://bucket-id/object-id` (other URI formats return\ngoogle.rpc.Code.INVALID_ARGUMENT). For more information, see\n[Request URIs](/storage/docs/reference-uris).\nA video URI may include wildcards in `object-id`, and thus identify\nmultiple videos. Supported wildcards: '*' to match 0 or more characters;\n'?' to match 1 character. If unset, the input video should be embedded\nin the request as `input_content`. If set, `input_content` should be unset.",
"type": "string"
},
"locationId": {
"description": "Optional. Cloud region where annotation should take place. Supported cloud\nregions: `us-east1`, `us-west1`, `europe-west1`, `asia-east1`. If no region\nis specified, a region will be determined based on video file location.",
"type": "string"
},
"outputUri": {
"description": "Optional. Location where the output (in JSON format) should be stored.\nCurrently, only [Cloud Storage](https://cloud.google.com/storage/)\nURIs are supported, which must be specified in the following format:\n`gs://bucket-id/object-id` (other URI formats return\ngoogle.rpc.Code.INVALID_ARGUMENT). For more information, see\n[Request URIs](/storage/docs/reference-uris).",
"type": "string"
},
"videoContext": {
"$ref": "GoogleCloudVideointelligenceV1_VideoContext",
"description": "Additional video context and/or feature-specific parameters."
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_AnnotateVideoResponse": {
"description": "Video annotation response. Included in the `response`\nfield of the `Operation` returned by the `GetOperation`\ncall of the `google::longrunning::Operations` service.",
"id": "GoogleCloudVideointelligenceV1_AnnotateVideoResponse",
"properties": {
"annotationResults": {
"description": "Annotation results for all videos specified in `AnnotateVideoRequest`.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_VideoAnnotationResults"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_Entity": {
"description": "Detected entity from video analysis.",
"id": "GoogleCloudVideointelligenceV1_Entity",
"properties": {
"description": {
"description": "Textual description, e.g. `Fixed-gear bicycle`.",
"type": "string"
},
"entityId": {
"description": "Opaque entity ID. Some IDs may be available in\n[Google Knowledge Graph Search\nAPI](https://developers.google.com/knowledge-graph/).",
"type": "string"
},
"languageCode": {
"description": "Language code for `description` in BCP-47 format.",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_ExplicitContentAnnotation": {
"description": "Explicit content annotation (based on per-frame visual signals only).\nIf no explicit content has been detected in a frame, no annotations are\npresent for that frame.",
"id": "GoogleCloudVideointelligenceV1_ExplicitContentAnnotation",
"properties": {
"frames": {
"description": "All video frames where explicit content was detected.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_ExplicitContentFrame"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_ExplicitContentDetectionConfig": {
"description": "Config for EXPLICIT_CONTENT_DETECTION.",
"id": "GoogleCloudVideointelligenceV1_ExplicitContentDetectionConfig",
"properties": {
"model": {
"description": "Model to use for explicit content detection.\nSupported values: \"builtin/stable\" (the default if unset) and\n\"builtin/latest\".",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_ExplicitContentFrame": {
"description": "Video frame level annotation results for explicit content.",
"id": "GoogleCloudVideointelligenceV1_ExplicitContentFrame",
"properties": {
"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"
},
"timeOffset": {
"description": "Time-offset, relative to the beginning of the video, corresponding to the\nvideo frame for this location.",
"format": "google-duration",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_LabelAnnotation": {
"description": "Label annotation.",
"id": "GoogleCloudVideointelligenceV1_LabelAnnotation",
"properties": {
"categoryEntities": {
"description": "Common categories for the detected entity.\nE.g. when the label is `Terrier` the category is likely `dog`. And in some\ncases there might be more than one categories e.g. `Terrier` could also be\na `pet`.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_Entity"
},
"type": "array"
},
"entity": {
"$ref": "GoogleCloudVideointelligenceV1_Entity",
"description": "Detected entity."
},
"frames": {
"description": "All video frames where a label was detected.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_LabelFrame"
},
"type": "array"
},
"segments": {
"description": "All video segments where a label was detected.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_LabelSegment"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_LabelDetectionConfig": {
"description": "Config for LABEL_DETECTION.",
"id": "GoogleCloudVideointelligenceV1_LabelDetectionConfig",
"properties": {
"frameConfidenceThreshold": {
"description": "The confidence threshold we perform filtering on the labels from\nframe-level detection. If not set, it is set to 0.4 by default. The valid\nrange for this threshold is [0.1, 0.9]. Any value set outside of this\nrange will be clipped.\nNote: for best results please follow the default threshold. We will update\nthe default threshold everytime when we release a new model.",
"format": "float",
"type": "number"
},
"labelDetectionMode": {
"description": "What labels should be detected with LABEL_DETECTION, in addition to\nvideo-level labels or segment-level labels.\nIf 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."
],
"type": "string"
},
"model": {
"description": "Model to use for label detection.\nSupported values: \"builtin/stable\" (the default if unset) and\n\"builtin/latest\".",
"type": "string"
},
"stationaryCamera": {
"description": "Whether the video has been shot from a stationary (i.e. non-moving) camera.\nWhen set to true, might improve detection accuracy for moving objects.\nShould be used with `SHOT_AND_FRAME_MODE` enabled.",
"type": "boolean"
},
"videoConfidenceThreshold": {
"description": "The confidence threshold we perform filtering on the labels from\nvideo-level and shot-level detections. If not set, it is set to 0.3 by\ndefault. The valid range for this threshold is [0.1, 0.9]. Any value set\noutside of this range will be clipped.\nNote: for best results please follow the default threshold. We will update\nthe default threshold everytime when we release a new model.",
"format": "float",
"type": "number"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_LabelFrame": {
"description": "Video frame level annotation results for label detection.",
"id": "GoogleCloudVideointelligenceV1_LabelFrame",
"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\nvideo frame for this location.",
"format": "google-duration",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_LabelSegment": {
"description": "Video segment level annotation results for label detection.",
"id": "GoogleCloudVideointelligenceV1_LabelSegment",
"properties": {
"confidence": {
"description": "Confidence that the label is accurate. Range: [0, 1].",
"format": "float",
"type": "number"
},
"segment": {
"$ref": "GoogleCloudVideointelligenceV1_VideoSegment",
"description": "Video segment where a label was detected."
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_NormalizedBoundingBox": {
"description": "Normalized bounding box.\nThe normalized vertex coordinates are relative to the original image.\nRange: [0, 1].",
"id": "GoogleCloudVideointelligenceV1_NormalizedBoundingBox",
"properties": {
"bottom": {
"description": "Bottom Y coordinate.",
"format": "float",
"type": "number"
},
"left": {
"description": "Left X coordinate.",
"format": "float",
"type": "number"
},
"right": {
"description": "Right X coordinate.",
"format": "float",
"type": "number"
},
"top": {
"description": "Top Y coordinate.",
"format": "float",
"type": "number"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_NormalizedBoundingPoly": {
"description": "Normalized bounding polygon for text (that might not be aligned with axis).\nContains list of the corner points in clockwise order starting from\ntop-left corner. For example, for a rectangular bounding box:\nWhen the text is horizontal it might look like:\n 0----1\n | |\n 3----2\n\nWhen it's clockwise rotated 180 degrees around the top-left corner it\nbecomes:\n 2----3\n | |\n 1----0\n\nand the vertex order will still be (0, 1, 2, 3). Note that values can be less\nthan 0, or greater than 1 due to trignometric calculations for location of\nthe box.",
"id": "GoogleCloudVideointelligenceV1_NormalizedBoundingPoly",
"properties": {
"vertices": {
"description": "Normalized vertices of the bounding polygon.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_NormalizedVertex"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_NormalizedVertex": {
"description": "A vertex represents a 2D point in the image.\nNOTE: the normalized vertex coordinates are relative to the original image\nand range from 0 to 1.",
"id": "GoogleCloudVideointelligenceV1_NormalizedVertex",
"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.",
"id": "GoogleCloudVideointelligenceV1_ObjectTrackingAnnotation",
"properties": {
"confidence": {
"description": "Object category's labeling confidence of this track.",
"format": "float",
"type": "number"
},
"entity": {
"$ref": "GoogleCloudVideointelligenceV1_Entity",
"description": "Entity to specify the object category that this track is labeled as."
},
"frames": {
"description": "Information corresponding to all frames where this object track appears.\nNon-streaming batch mode: it may be one or multiple ObjectTrackingFrame\nmessages in frames.\nStreaming mode: it can only be one ObjectTrackingFrame message in frames.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_ObjectTrackingFrame"
},
"type": "array"
},
"segment": {
"$ref": "GoogleCloudVideointelligenceV1_VideoSegment",
"description": "Non-streaming batch mode ONLY.\nEach object track corresponds to one video segment where it appears."
},
"trackId": {
"description": "Streaming mode ONLY.\nIn streaming mode, we do not know the end time of a tracked object\nbefore it is completed. Hence, there is no VideoSegment info returned.\nInstead, we provide a unique identifiable integer track_id so that\nthe customers can correlate the results of the ongoing\nObjectTrackAnnotation of the same track_id over time.",
"format": "int64",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_ObjectTrackingConfig": {
"description": "Config for OBJECT_TRACKING.",
"id": "GoogleCloudVideointelligenceV1_ObjectTrackingConfig",
"properties": {
"model": {
"description": "Model to use for object tracking.\nSupported values: \"builtin/stable\" (the default if unset) and\n\"builtin/latest\".",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_ObjectTrackingFrame": {
"description": "Video frame level annotations for object detection and tracking. This field\nstores per frame location, time offset, and confidence.",
"id": "GoogleCloudVideointelligenceV1_ObjectTrackingFrame",
"properties": {
"normalizedBoundingBox": {
"$ref": "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_ShotChangeDetectionConfig": {
"description": "Config for SHOT_CHANGE_DETECTION.",
"id": "GoogleCloudVideointelligenceV1_ShotChangeDetectionConfig",
"properties": {
"model": {
"description": "Model to use for shot change detection.\nSupported values: \"builtin/stable\" (the default if unset) and\n\"builtin/latest\".",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_SpeechContext": {
"description": "Provides \"hints\" to the speech recognizer to favor specific words and phrases\nin the results.",
"id": "GoogleCloudVideointelligenceV1_SpeechContext",
"properties": {
"phrases": {
"description": "Optional. A list of strings containing words and phrases \"hints\" so that\nthe speech recognition is more likely to recognize them. This can be used\nto improve the accuracy for specific words and phrases, for example, if\nspecific commands are typically spoken by the user. This can also be used\nto add additional words to the vocabulary of the recognizer. See\n[usage limits](https://cloud.google.com/speech/limits#content).",
"items": {
"type": "string"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_SpeechRecognitionAlternative": {
"description": "Alternative hypotheses (a.k.a. n-best list).",
"id": "GoogleCloudVideointelligenceV1_SpeechRecognitionAlternative",
"properties": {
"confidence": {
"description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number\nindicates an estimated greater likelihood that the recognized words are\ncorrect. This field is set only for the top alternative.\nThis field is not guaranteed to be accurate and users should not rely on it\nto be always provided.\nThe default of 0.0 is a sentinel value indicating `confidence` was not set.",
"format": "float",
"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.\nNote: When `enable_speaker_diarization` is true, you will see all the words\nfrom the beginning of the audio.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_WordInfo"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_SpeechTranscription": {
"description": "A speech recognition result corresponding to a portion of the audio.",
"id": "GoogleCloudVideointelligenceV1_SpeechTranscription",
"properties": {
"alternatives": {
"description": "May contain one or more recognition hypotheses (up to the maximum specified\nin `max_alternatives`). These alternatives are ordered in terms of\naccuracy, with the top (first) alternative being the most probable, as\nranked by the recognizer.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_SpeechRecognitionAlternative"
},
"type": "array"
},
"languageCode": {
"description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of\nthe language in this result. This language code was detected to have the\nmost likelihood of being spoken in the audio.",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_SpeechTranscriptionConfig": {
"description": "Config for SPEECH_TRANSCRIPTION.",
"id": "GoogleCloudVideointelligenceV1_SpeechTranscriptionConfig",
"properties": {
"audioTracks": {
"description": "Optional. For file formats, such as MXF or MKV, supporting multiple audio\ntracks, specify up to two tracks. Default: track 0.",
"items": {
"format": "int32",
"type": "integer"
},
"type": "array"
},
"diarizationSpeakerCount": {
"description": "Optional. If set, specifies the estimated number of speakers in the conversation.\nIf not set, defaults to '2'.\nIgnored unless enable_speaker_diarization is set to true.",
"format": "int32",
"type": "integer"
},
"enableAutomaticPunctuation": {
"description": "Optional. If 'true', adds punctuation to recognition result hypotheses.\nThis feature is only available in select languages. Setting this for\nrequests in other languages has no effect at all. The default 'false' value\ndoes not add punctuation to result hypotheses. NOTE: \"This is currently\noffered as an experimental service, complimentary to all users. In the\nfuture this may be exclusively available as a premium feature.\"",
"type": "boolean"
},
"enableSpeakerDiarization": {
"description": "Optional. If 'true', enables speaker detection for each recognized word in\nthe top alternative of the recognition result using a speaker_tag provided\nin the WordInfo.\nNote: When this is true, we send all the words from the beginning of the\naudio for the top alternative in every consecutive responses.\nThis is done in order to improve our speaker tags as our models learn to\nidentify the speakers in the conversation over time.",
"type": "boolean"
},
"enableWordConfidence": {
"description": "Optional. If `true`, the top result includes a list of words and the\nconfidence for those words. If `false`, no word-level confidence\ninformation is returned. The default is `false`.",
"type": "boolean"
},
"filterProfanity": {
"description": "Optional. If set to `true`, the server will attempt to filter out\nprofanities, replacing all but the initial character in each filtered word\nwith asterisks, e.g. \"f***\". If set to `false` or omitted, profanities\nwon't be filtered out.",
"type": "boolean"
},
"languageCode": {
"description": "Required. *Required* The language of the supplied audio as a\n[BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.\nExample: \"en-US\".\nSee [Language Support](https://cloud.google.com/speech/docs/languages)\nfor a list of the currently supported language codes.",
"type": "string"
},
"maxAlternatives": {
"description": "Optional. Maximum number of recognition hypotheses to be returned.\nSpecifically, the maximum number of `SpeechRecognitionAlternative` messages\nwithin each `SpeechTranscription`. The server may return fewer than\n`max_alternatives`. Valid values are `0`-`30`. A value of `0` or `1` will\nreturn a maximum of one. If omitted, will return a maximum of one.",
"format": "int32",
"type": "integer"
},
"speechContexts": {
"description": "Optional. A means to provide context to assist the speech recognition.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_SpeechContext"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_TextAnnotation": {
"description": "Annotations related to one detected OCR text snippet. This will contain the\ncorresponding text, confidence value, and frame level information for each\ndetection.",
"id": "GoogleCloudVideointelligenceV1_TextAnnotation",
"properties": {
"segments": {
"description": "All video segments where OCR detected text appears.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_TextSegment"
},
"type": "array"
},
"text": {
"description": "The detected text.",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_TextDetectionConfig": {
"description": "Config for TEXT_DETECTION.",
"id": "GoogleCloudVideointelligenceV1_TextDetectionConfig",
"properties": {
"languageHints": {
"description": "Language hint can be specified if the language to be detected is known a\npriori. It can increase the accuracy of the detection. Language hint must\nbe language code in BCP-47 format.\n\nAutomatic language detection is performed if no hint is provided.",
"items": {
"type": "string"
},
"type": "array"
},
"model": {
"description": "Model to use for text detection.\nSupported values: \"builtin/stable\" (the default if unset) and\n\"builtin/latest\".",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_TextFrame": {
"description": "Video frame level annotation results for text annotation (OCR).\nContains information regarding timestamp and bounding box locations for the\nframes containing detected OCR text snippets.",
"id": "GoogleCloudVideointelligenceV1_TextFrame",
"properties": {
"rotatedBoundingBox": {
"$ref": "GoogleCloudVideointelligenceV1_NormalizedBoundingPoly",
"description": "Bounding polygon of the detected text for this frame."
},
"timeOffset": {
"description": "Timestamp of this frame.",
"format": "google-duration",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_TextSegment": {
"description": "Video segment level annotation results for text detection.",
"id": "GoogleCloudVideointelligenceV1_TextSegment",
"properties": {
"confidence": {
"description": "Confidence for the track of detected text. It is calculated as the highest\nover all frames where OCR detected text appears.",
"format": "float",
"type": "number"
},
"frames": {
"description": "Information related to the frames where OCR detected text appears.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_TextFrame"
},
"type": "array"
},
"segment": {
"$ref": "GoogleCloudVideointelligenceV1_VideoSegment",
"description": "Video segment where a text snippet was detected."
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_VideoAnnotationProgress": {
"description": "Annotation progress for a single video.",
"id": "GoogleCloudVideointelligenceV1_VideoAnnotationProgress",
"properties": {
"feature": {
"description": "Specifies which feature is being tracked if the request contains more than\none features.",
"enum": [
"FEATURE_UNSPECIFIED",
"LABEL_DETECTION",
"SHOT_CHANGE_DETECTION",
"EXPLICIT_CONTENT_DETECTION",
"SPEECH_TRANSCRIPTION",
"TEXT_DETECTION",
"OBJECT_TRACKING"
],
"enumDescriptions": [
"Unspecified.",
"Label detection. Detect objects, such as dog or flower.",
"Shot change detection.",
"Explicit content detection.",
"Speech transcription.",
"OCR text detection and tracking.",
"Object detection and tracking."
],
"type": "string"
},
"inputUri": {
"description": "Video file location in\n[Cloud Storage](https://cloud.google.com/storage/).",
"type": "string"
},
"progressPercent": {
"description": "Approximate percentage processed thus far. Guaranteed to be\n100 when fully processed.",
"format": "int32",
"type": "integer"
},
"segment": {
"$ref": "GoogleCloudVideointelligenceV1_VideoSegment",
"description": "Specifies which segment is being tracked if the request contains more than\none segments."
},
"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.",
"id": "GoogleCloudVideointelligenceV1_VideoAnnotationResults",
"properties": {
"error": {
"$ref": "GoogleRpc_Status",
"description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest`\nsome videos may succeed and some may fail."
},
"explicitAnnotation": {
"$ref": "GoogleCloudVideointelligenceV1_ExplicitContentAnnotation",
"description": "Explicit content annotation."
},
"frameLabelAnnotations": {
"description": "Label annotations on frame level.\nThere is exactly one element for each unique label.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation"
},
"type": "array"
},
"inputUri": {
"description": "Video file location in\n[Cloud Storage](https://cloud.google.com/storage/).",
"type": "string"
},
"objectAnnotations": {
"description": "Annotations for list of objects detected and tracked in video.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_ObjectTrackingAnnotation"
},
"type": "array"
},
"segment": {
"$ref": "GoogleCloudVideointelligenceV1_VideoSegment",
"description": "Video segment on which the annotation is run."
},
"segmentLabelAnnotations": {
"description": "Topical label annotations on video level or user specified segment level.\nThere is exactly one element for each unique label.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation"
},
"type": "array"
},
"segmentPresenceLabelAnnotations": {
"description": "Presence label annotations on video level or user specified segment level.\nThere is exactly one element for each unique label. Compared to the\nexisting topical `segment_label_annotations`, this field presents more\nfine-grained, segment-level labels detected in video content and is made\navailable only when the client sets `LabelDetectionConfig.model` to\n\"builtin/latest\" in the request.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation"
},
"type": "array"
},
"shotAnnotations": {
"description": "Shot annotations. Each shot is represented as a video segment.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_VideoSegment"
},
"type": "array"
},
"shotLabelAnnotations": {
"description": "Topical label annotations on shot level.\nThere is exactly one element for each unique label.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation"
},
"type": "array"
},
"shotPresenceLabelAnnotations": {
"description": "Presence label annotations on shot level. There is exactly one element for\neach unique label. Compared to the existing topical\n`shot_label_annotations`, this field presents more fine-grained, shot-level\nlabels detected in video content and is made available only when the client\nsets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation"
},
"type": "array"
},
"speechTranscriptions": {
"description": "Speech transcription.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_SpeechTranscription"
},
"type": "array"
},
"textAnnotations": {
"description": "OCR text detection and tracking.\nAnnotations for list of detected text snippets. Each will have list of\nframe information associated with it.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_TextAnnotation"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_VideoContext": {
"description": "Video context and/or feature-specific parameters.",
"id": "GoogleCloudVideointelligenceV1_VideoContext",
"properties": {
"explicitContentDetectionConfig": {
"$ref": "GoogleCloudVideointelligenceV1_ExplicitContentDetectionConfig",
"description": "Config for EXPLICIT_CONTENT_DETECTION."
},
"labelDetectionConfig": {
"$ref": "GoogleCloudVideointelligenceV1_LabelDetectionConfig",
"description": "Config for LABEL_DETECTION."
},
"objectTrackingConfig": {
"$ref": "GoogleCloudVideointelligenceV1_ObjectTrackingConfig",
"description": "Config for OBJECT_TRACKING."
},
"segments": {
"description": "Video segments to annotate. The segments may overlap and are not required\nto be contiguous or span the whole video. If unspecified, each video is\ntreated as a single segment.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1_VideoSegment"
},
"type": "array"
},
"shotChangeDetectionConfig": {
"$ref": "GoogleCloudVideointelligenceV1_ShotChangeDetectionConfig",
"description": "Config for SHOT_CHANGE_DETECTION."
},
"speechTranscriptionConfig": {
"$ref": "GoogleCloudVideointelligenceV1_SpeechTranscriptionConfig",
"description": "Config for SPEECH_TRANSCRIPTION."
},
"textDetectionConfig": {
"$ref": "GoogleCloudVideointelligenceV1_TextDetectionConfig",
"description": "Config for TEXT_DETECTION."
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1_VideoSegment": {
"description": "Video segment.",
"id": "GoogleCloudVideointelligenceV1_VideoSegment",
"properties": {
"endTimeOffset": {
"description": "Time-offset, relative to the beginning of the video,\ncorresponding to the end of the segment (inclusive).",
"format": "google-duration",
"type": "string"
},
"startTimeOffset": {
"description": "Time-offset, relative to the beginning of the video,\ncorresponding 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\nincluded in the response when certain request parameters are set, such\nas `enable_word_time_offsets`.",
"id": "GoogleCloudVideointelligenceV1_WordInfo",
"properties": {
"confidence": {
"description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number\nindicates an estimated greater likelihood that the recognized words are\ncorrect. This field is set only for the top alternative.\nThis field is not guaranteed to be accurate and users should not rely on it\nto be always provided.\nThe default of 0.0 is a sentinel value indicating `confidence` was not set.",
"format": "float",
"type": "number"
},
"endTime": {
"description": "Time offset relative to the beginning of the audio, and\ncorresponding to the end of the spoken word. This field is only set if\n`enable_word_time_offsets=true` and only in the top hypothesis. This is an\nexperimental 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\nthe audio. This field specifies which one of those speakers was detected to\nhave spoken this word. Value ranges from 1 up to diarization_speaker_count,\nand is only set if speaker diarization is enabled.",
"format": "int32",
"type": "integer"
},
"startTime": {
"description": "Time offset relative to the beginning of the audio, and\ncorresponding to the start of the spoken word. This field is only set if\n`enable_word_time_offsets=true` and only in the top hypothesis. This is an\nexperimental 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`\nfield of the `Operation` returned by the `GetOperation`\ncall of the `google::longrunning::Operations` service.",
"id": "GoogleCloudVideointelligenceV1beta2_AnnotateVideoProgress",
"properties": {
"annotationProgress": {
"description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationProgress"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1beta2_AnnotateVideoResponse": {
"description": "Video annotation response. Included in the `response`\nfield of the `Operation` returned by the `GetOperation`\ncall of the `google::longrunning::Operations` service.",
"id": "GoogleCloudVideointelligenceV1beta2_AnnotateVideoResponse",
"properties": {
"annotationResults": {
"description": "Annotation results for all videos specified in `AnnotateVideoRequest`.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationResults"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1beta2_Entity": {
"description": "Detected entity from video analysis.",
"id": "GoogleCloudVideointelligenceV1beta2_Entity",
"properties": {
"description": {
"description": "Textual description, e.g. `Fixed-gear bicycle`.",
"type": "string"
},
"entityId": {
"description": "Opaque entity ID. Some IDs may be available in\n[Google Knowledge Graph Search\nAPI](https://developers.google.com/knowledge-graph/).",
"type": "string"
},
"languageCode": {
"description": "Language code for `description` in BCP-47 format.",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1beta2_ExplicitContentAnnotation": {
"description": "Explicit content annotation (based on per-frame visual signals only).\nIf no explicit content has been detected in a frame, no annotations are\npresent for that frame.",
"id": "GoogleCloudVideointelligenceV1beta2_ExplicitContentAnnotation",
"properties": {
"frames": {
"description": "All video frames where explicit content was detected.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1beta2_ExplicitContentFrame"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1beta2_ExplicitContentFrame": {
"description": "Video frame level annotation results for explicit content.",
"id": "GoogleCloudVideointelligenceV1beta2_ExplicitContentFrame",
"properties": {
"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"
},
"timeOffset": {
"description": "Time-offset, relative to the beginning of the video, corresponding to the\nvideo frame for this location.",
"format": "google-duration",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1beta2_LabelAnnotation": {
"description": "Label annotation.",
"id": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation",
"properties": {
"categoryEntities": {
"description": "Common categories for the detected entity.\nE.g. when the label is `Terrier` the category is likely `dog`. And in some\ncases there might be more than one categories e.g. `Terrier` could also be\na `pet`.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1beta2_Entity"
},
"type": "array"
},
"entity": {
"$ref": "GoogleCloudVideointelligenceV1beta2_Entity",
"description": "Detected entity."
},
"frames": {
"description": "All video frames where a label was detected.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1beta2_LabelFrame"
},
"type": "array"
},
"segments": {
"description": "All video segments where a label was detected.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1beta2_LabelSegment"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1beta2_LabelFrame": {
"description": "Video frame level annotation results for label detection.",
"id": "GoogleCloudVideointelligenceV1beta2_LabelFrame",
"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\nvideo frame for this location.",
"format": "google-duration",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1beta2_LabelSegment": {
"description": "Video segment level annotation results for label detection.",
"id": "GoogleCloudVideointelligenceV1beta2_LabelSegment",
"properties": {
"confidence": {
"description": "Confidence that the label is accurate. Range: [0, 1].",
"format": "float",
"type": "number"
},
"segment": {
"$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment",
"description": "Video segment where a label was detected."
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox": {
"description": "Normalized bounding box.\nThe normalized vertex coordinates are relative to the original image.\nRange: [0, 1].",
"id": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox",
"properties": {
"bottom": {
"description": "Bottom Y coordinate.",
"format": "float",
"type": "number"
},
"left": {
"description": "Left X coordinate.",
"format": "float",
"type": "number"
},
"right": {
"description": "Right X coordinate.",
"format": "float",
"type": "number"
},
"top": {
"description": "Top Y coordinate.",
"format": "float",
"type": "number"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1beta2_NormalizedBoundingPoly": {
"description": "Normalized bounding polygon for text (that might not be aligned with axis).\nContains list of the corner points in clockwise order starting from\ntop-left corner. For example, for a rectangular bounding box:\nWhen the text is horizontal it might look like:\n 0----1\n | |\n 3----2\n\nWhen it's clockwise rotated 180 degrees around the top-left corner it\nbecomes:\n 2----3\n | |\n 1----0\n\nand the vertex order will still be (0, 1, 2, 3). Note that values can be less\nthan 0, or greater than 1 due to trignometric calculations for location of\nthe box.",
"id": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingPoly",
"properties": {
"vertices": {
"description": "Normalized vertices of the bounding polygon.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedVertex"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1beta2_NormalizedVertex": {
"description": "A vertex represents a 2D point in the image.\nNOTE: the normalized vertex coordinates are relative to the original image\nand range from 0 to 1.",
"id": "GoogleCloudVideointelligenceV1beta2_NormalizedVertex",
"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.",
"id": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingAnnotation",
"properties": {
"confidence": {
"description": "Object category's labeling confidence of this track.",
"format": "float",
"type": "number"
},
"entity": {
"$ref": "GoogleCloudVideointelligenceV1beta2_Entity",
"description": "Entity to specify the object category that this track is labeled as."
},
"frames": {
"description": "Information corresponding to all frames where this object track appears.\nNon-streaming batch mode: it may be one or multiple ObjectTrackingFrame\nmessages in frames.\nStreaming mode: it can only be one ObjectTrackingFrame message in frames.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingFrame"
},
"type": "array"
},
"segment": {
"$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment",
"description": "Non-streaming batch mode ONLY.\nEach object track corresponds to one video segment where it appears."
},
"trackId": {
"description": "Streaming mode ONLY.\nIn streaming mode, we do not know the end time of a tracked object\nbefore it is completed. Hence, there is no VideoSegment info returned.\nInstead, we provide a unique identifiable integer track_id so that\nthe customers can correlate the results of the ongoing\nObjectTrackAnnotation of the same track_id over time.",
"format": "int64",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1beta2_ObjectTrackingFrame": {
"description": "Video frame level annotations for object detection and tracking. This field\nstores per frame location, time offset, and confidence.",
"id": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingFrame",
"properties": {
"normalizedBoundingBox": {
"$ref": "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_SpeechRecognitionAlternative": {
"description": "Alternative hypotheses (a.k.a. n-best list).",
"id": "GoogleCloudVideointelligenceV1beta2_SpeechRecognitionAlternative",
"properties": {
"confidence": {
"description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number\nindicates an estimated greater likelihood that the recognized words are\ncorrect. This field is set only for the top alternative.\nThis field is not guaranteed to be accurate and users should not rely on it\nto be always provided.\nThe default of 0.0 is a sentinel value indicating `confidence` was not set.",
"format": "float",
"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.\nNote: When `enable_speaker_diarization` is true, you will see all the words\nfrom the beginning of the audio.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1beta2_WordInfo"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1beta2_SpeechTranscription": {
"description": "A speech recognition result corresponding to a portion of the audio.",
"id": "GoogleCloudVideointelligenceV1beta2_SpeechTranscription",
"properties": {
"alternatives": {
"description": "May contain one or more recognition hypotheses (up to the maximum specified\nin `max_alternatives`). These alternatives are ordered in terms of\naccuracy, with the top (first) alternative being the most probable, as\nranked by the recognizer.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1beta2_SpeechRecognitionAlternative"
},
"type": "array"
},
"languageCode": {
"description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of\nthe language in this result. This language code was detected to have the\nmost likelihood of being spoken in the audio.",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1beta2_TextAnnotation": {
"description": "Annotations related to one detected OCR text snippet. This will contain the\ncorresponding text, confidence value, and frame level information for each\ndetection.",
"id": "GoogleCloudVideointelligenceV1beta2_TextAnnotation",
"properties": {
"segments": {
"description": "All video segments where OCR detected text appears.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1beta2_TextSegment"
},
"type": "array"
},
"text": {
"description": "The detected text.",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1beta2_TextFrame": {
"description": "Video frame level annotation results for text annotation (OCR).\nContains information regarding timestamp and bounding box locations for the\nframes containing detected OCR text snippets.",
"id": "GoogleCloudVideointelligenceV1beta2_TextFrame",
"properties": {
"rotatedBoundingBox": {
"$ref": "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.",
"id": "GoogleCloudVideointelligenceV1beta2_TextSegment",
"properties": {
"confidence": {
"description": "Confidence for the track of detected text. It is calculated as the highest\nover all frames where OCR detected text appears.",
"format": "float",
"type": "number"
},
"frames": {
"description": "Information related to the frames where OCR detected text appears.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1beta2_TextFrame"
},
"type": "array"
},
"segment": {
"$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment",
"description": "Video segment where a text snippet was detected."
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1beta2_VideoAnnotationProgress": {
"description": "Annotation progress for a single video.",
"id": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationProgress",
"properties": {
"feature": {
"description": "Specifies which feature is being tracked if the request contains more than\none features.",
"enum": [
"FEATURE_UNSPECIFIED",
"LABEL_DETECTION",
"SHOT_CHANGE_DETECTION",
"EXPLICIT_CONTENT_DETECTION",
"SPEECH_TRANSCRIPTION",
"TEXT_DETECTION",
"OBJECT_TRACKING"
],
"enumDescriptions": [
"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."
],
"type": "string"
},
"inputUri": {
"description": "Video file location in\n[Cloud Storage](https://cloud.google.com/storage/).",
"type": "string"
},
"progressPercent": {
"description": "Approximate percentage processed thus far. Guaranteed to be\n100 when fully processed.",
"format": "int32",
"type": "integer"
},
"segment": {
"$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment",
"description": "Specifies which segment is being tracked if the request contains more than\none segments."
},
"startTime": {
"description": "Time when the request was received.",
"format": "google-datetime",
"type": "string"
},
"updateTime": {
"description": "Time of the most recent update.",
"format": "google-datetime",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1beta2_VideoAnnotationResults": {
"description": "Annotation results for a single video.",
"id": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationResults",
"properties": {
"error": {
"$ref": "GoogleRpc_Status",
"description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest`\nsome videos may succeed and some may fail."
},
"explicitAnnotation": {
"$ref": "GoogleCloudVideointelligenceV1beta2_ExplicitContentAnnotation",
"description": "Explicit content annotation."
},
"frameLabelAnnotations": {
"description": "Label annotations on frame level.\nThere is exactly one element for each unique label.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation"
},
"type": "array"
},
"inputUri": {
"description": "Video file location in\n[Cloud Storage](https://cloud.google.com/storage/).",
"type": "string"
},
"objectAnnotations": {
"description": "Annotations for list of objects detected and tracked in video.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingAnnotation"
},
"type": "array"
},
"segment": {
"$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment",
"description": "Video segment on which the annotation is run."
},
"segmentLabelAnnotations": {
"description": "Topical label annotations on video level or user specified segment level.\nThere is exactly one element for each unique label.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation"
},
"type": "array"
},
"segmentPresenceLabelAnnotations": {
"description": "Presence label annotations on video level or user specified segment level.\nThere is exactly one element for each unique label. Compared to the\nexisting topical `segment_label_annotations`, this field presents more\nfine-grained, segment-level labels detected in video content and is made\navailable only when the client sets `LabelDetectionConfig.model` to\n\"builtin/latest\" in the request.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation"
},
"type": "array"
},
"shotAnnotations": {
"description": "Shot annotations. Each shot is represented as a video segment.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment"
},
"type": "array"
},
"shotLabelAnnotations": {
"description": "Topical label annotations on shot level.\nThere is exactly one element for each unique label.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation"
},
"type": "array"
},
"shotPresenceLabelAnnotations": {
"description": "Presence label annotations on shot level. There is exactly one element for\neach unique label. Compared to the existing topical\n`shot_label_annotations`, this field presents more fine-grained, shot-level\nlabels detected in video content and is made available only when the client\nsets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation"
},
"type": "array"
},
"speechTranscriptions": {
"description": "Speech transcription.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1beta2_SpeechTranscription"
},
"type": "array"
},
"textAnnotations": {
"description": "OCR text detection and tracking.\nAnnotations for list of detected text snippets. Each will have list of\nframe information associated with it.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1beta2_TextAnnotation"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1beta2_VideoSegment": {
"description": "Video segment.",
"id": "GoogleCloudVideointelligenceV1beta2_VideoSegment",
"properties": {
"endTimeOffset": {
"description": "Time-offset, relative to the beginning of the video,\ncorresponding to the end of the segment (inclusive).",
"format": "google-duration",
"type": "string"
},
"startTimeOffset": {
"description": "Time-offset, relative to the beginning of the video,\ncorresponding to the start of the segment (inclusive).",
"format": "google-duration",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1beta2_WordInfo": {
"description": "Word-specific information for recognized words. Word information is only\nincluded in the response when certain request parameters are set, such\nas `enable_word_time_offsets`.",
"id": "GoogleCloudVideointelligenceV1beta2_WordInfo",
"properties": {
"confidence": {
"description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number\nindicates an estimated greater likelihood that the recognized words are\ncorrect. This field is set only for the top alternative.\nThis field is not guaranteed to be accurate and users should not rely on it\nto be always provided.\nThe default of 0.0 is a sentinel value indicating `confidence` was not set.",
"format": "float",
"type": "number"
},
"endTime": {
"description": "Time offset relative to the beginning of the audio, and\ncorresponding to the end of the spoken word. This field is only set if\n`enable_word_time_offsets=true` and only in the top hypothesis. This is an\nexperimental 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\nthe audio. This field specifies which one of those speakers was detected to\nhave spoken this word. Value ranges from 1 up to diarization_speaker_count,\nand is only set if speaker diarization is enabled.",
"format": "int32",
"type": "integer"
},
"startTime": {
"description": "Time offset relative to the beginning of the audio, and\ncorresponding to the start of the spoken word. This field is only set if\n`enable_word_time_offsets=true` and only in the top hypothesis. This is an\nexperimental 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"
},
"GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoProgress": {
"description": "Video annotation progress. Included in the `metadata`\nfield of the `Operation` returned by the `GetOperation`\ncall of the `google::longrunning::Operations` service.",
"id": "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoProgress",
"properties": {
"annotationProgress": {
"description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationProgress"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoResponse": {
"description": "Video annotation response. Included in the `response`\nfield of the `Operation` returned by the `GetOperation`\ncall of the `google::longrunning::Operations` service.",
"id": "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoResponse",
"properties": {
"annotationResults": {
"description": "Annotation results for all videos specified in `AnnotateVideoRequest`.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationResults"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p1beta1_Entity": {
"description": "Detected entity from video analysis.",
"id": "GoogleCloudVideointelligenceV1p1beta1_Entity",
"properties": {
"description": {
"description": "Textual description, e.g. `Fixed-gear bicycle`.",
"type": "string"
},
"entityId": {
"description": "Opaque entity ID. Some IDs may be available in\n[Google Knowledge Graph Search\nAPI](https://developers.google.com/knowledge-graph/).",
"type": "string"
},
"languageCode": {
"description": "Language code for `description` in BCP-47 format.",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p1beta1_ExplicitContentAnnotation": {
"description": "Explicit content annotation (based on per-frame visual signals only).\nIf no explicit content has been detected in a frame, no annotations are\npresent for that frame.",
"id": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentAnnotation",
"properties": {
"frames": {
"description": "All video frames where explicit content was detected.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentFrame"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p1beta1_ExplicitContentFrame": {
"description": "Video frame level annotation results for explicit content.",
"id": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentFrame",
"properties": {
"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"
},
"timeOffset": {
"description": "Time-offset, relative to the beginning of the video, corresponding to the\nvideo frame for this location.",
"format": "google-duration",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation": {
"description": "Label annotation.",
"id": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation",
"properties": {
"categoryEntities": {
"description": "Common categories for the detected entity.\nE.g. when the label is `Terrier` the category is likely `dog`. And in some\ncases there might be more than one categories e.g. `Terrier` could also be\na `pet`.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity"
},
"type": "array"
},
"entity": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity",
"description": "Detected entity."
},
"frames": {
"description": "All video frames where a label was detected.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelFrame"
},
"type": "array"
},
"segments": {
"description": "All video segments where a label was detected.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelSegment"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p1beta1_LabelFrame": {
"description": "Video frame level annotation results for label detection.",
"id": "GoogleCloudVideointelligenceV1p1beta1_LabelFrame",
"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\nvideo frame for this location.",
"format": "google-duration",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p1beta1_LabelSegment": {
"description": "Video segment level annotation results for label detection.",
"id": "GoogleCloudVideointelligenceV1p1beta1_LabelSegment",
"properties": {
"confidence": {
"description": "Confidence that the label is accurate. Range: [0, 1].",
"format": "float",
"type": "number"
},
"segment": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment",
"description": "Video segment where a label was detected."
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox": {
"description": "Normalized bounding box.\nThe normalized vertex coordinates are relative to the original image.\nRange: [0, 1].",
"id": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox",
"properties": {
"bottom": {
"description": "Bottom Y coordinate.",
"format": "float",
"type": "number"
},
"left": {
"description": "Left X coordinate.",
"format": "float",
"type": "number"
},
"right": {
"description": "Right X coordinate.",
"format": "float",
"type": "number"
},
"top": {
"description": "Top Y coordinate.",
"format": "float",
"type": "number"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingPoly": {
"description": "Normalized bounding polygon for text (that might not be aligned with axis).\nContains list of the corner points in clockwise order starting from\ntop-left corner. For example, for a rectangular bounding box:\nWhen the text is horizontal it might look like:\n 0----1\n | |\n 3----2\n\nWhen it's clockwise rotated 180 degrees around the top-left corner it\nbecomes:\n 2----3\n | |\n 1----0\n\nand the vertex order will still be (0, 1, 2, 3). Note that values can be less\nthan 0, or greater than 1 due to trignometric calculations for location of\nthe box.",
"id": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingPoly",
"properties": {
"vertices": {
"description": "Normalized vertices of the bounding polygon.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex": {
"description": "A vertex represents a 2D point in the image.\nNOTE: the normalized vertex coordinates are relative to the original image\nand range from 0 to 1.",
"id": "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex",
"properties": {
"x": {
"description": "X coordinate.",
"format": "float",
"type": "number"
},
"y": {
"description": "Y coordinate.",
"format": "float",
"type": "number"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingAnnotation": {
"description": "Annotations corresponding to one tracked object.",
"id": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingAnnotation",
"properties": {
"confidence": {
"description": "Object category's labeling confidence of this track.",
"format": "float",
"type": "number"
},
"entity": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity",
"description": "Entity to specify the object category that this track is labeled as."
},
"frames": {
"description": "Information corresponding to all frames where this object track appears.\nNon-streaming batch mode: it may be one or multiple ObjectTrackingFrame\nmessages in frames.\nStreaming mode: it can only be one ObjectTrackingFrame message in frames.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingFrame"
},
"type": "array"
},
"segment": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment",
"description": "Non-streaming batch mode ONLY.\nEach object track corresponds to one video segment where it appears."
},
"trackId": {
"description": "Streaming mode ONLY.\nIn streaming mode, we do not know the end time of a tracked object\nbefore it is completed. Hence, there is no VideoSegment info returned.\nInstead, we provide a unique identifiable integer track_id so that\nthe customers can correlate the results of the ongoing\nObjectTrackAnnotation of the same track_id over time.",
"format": "int64",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingFrame": {
"description": "Video frame level annotations for object detection and tracking. This field\nstores per frame location, time offset, and confidence.",
"id": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingFrame",
"properties": {
"normalizedBoundingBox": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_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"
},
"GoogleCloudVideointelligenceV1p1beta1_SpeechRecognitionAlternative": {
"description": "Alternative hypotheses (a.k.a. n-best list).",
"id": "GoogleCloudVideointelligenceV1p1beta1_SpeechRecognitionAlternative",
"properties": {
"confidence": {
"description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number\nindicates an estimated greater likelihood that the recognized words are\ncorrect. This field is set only for the top alternative.\nThis field is not guaranteed to be accurate and users should not rely on it\nto be always provided.\nThe default of 0.0 is a sentinel value indicating `confidence` was not set.",
"format": "float",
"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.\nNote: When `enable_speaker_diarization` is true, you will see all the words\nfrom the beginning of the audio.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_WordInfo"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p1beta1_SpeechTranscription": {
"description": "A speech recognition result corresponding to a portion of the audio.",
"id": "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscription",
"properties": {
"alternatives": {
"description": "May contain one or more recognition hypotheses (up to the maximum specified\nin `max_alternatives`). These alternatives are ordered in terms of\naccuracy, with the top (first) alternative being the most probable, as\nranked by the recognizer.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_SpeechRecognitionAlternative"
},
"type": "array"
},
"languageCode": {
"description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of\nthe language in this result. This language code was detected to have the\nmost likelihood of being spoken in the audio.",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p1beta1_TextAnnotation": {
"description": "Annotations related to one detected OCR text snippet. This will contain the\ncorresponding text, confidence value, and frame level information for each\ndetection.",
"id": "GoogleCloudVideointelligenceV1p1beta1_TextAnnotation",
"properties": {
"segments": {
"description": "All video segments where OCR detected text appears.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_TextSegment"
},
"type": "array"
},
"text": {
"description": "The detected text.",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p1beta1_TextFrame": {
"description": "Video frame level annotation results for text annotation (OCR).\nContains information regarding timestamp and bounding box locations for the\nframes containing detected OCR text snippets.",
"id": "GoogleCloudVideointelligenceV1p1beta1_TextFrame",
"properties": {
"rotatedBoundingBox": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingPoly",
"description": "Bounding polygon of the detected text for this frame."
},
"timeOffset": {
"description": "Timestamp of this frame.",
"format": "google-duration",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p1beta1_TextSegment": {
"description": "Video segment level annotation results for text detection.",
"id": "GoogleCloudVideointelligenceV1p1beta1_TextSegment",
"properties": {
"confidence": {
"description": "Confidence for the track of detected text. It is calculated as the highest\nover all frames where OCR detected text appears.",
"format": "float",
"type": "number"
},
"frames": {
"description": "Information related to the frames where OCR detected text appears.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_TextFrame"
},
"type": "array"
},
"segment": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment",
"description": "Video segment where a text snippet was detected."
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationProgress": {
"description": "Annotation progress for a single video.",
"id": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationProgress",
"properties": {
"feature": {
"description": "Specifies which feature is being tracked if the request contains more than\none features.",
"enum": [
"FEATURE_UNSPECIFIED",
"LABEL_DETECTION",
"SHOT_CHANGE_DETECTION",
"EXPLICIT_CONTENT_DETECTION",
"SPEECH_TRANSCRIPTION",
"TEXT_DETECTION",
"OBJECT_TRACKING"
],
"enumDescriptions": [
"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."
],
"type": "string"
},
"inputUri": {
"description": "Video file location in\n[Cloud Storage](https://cloud.google.com/storage/).",
"type": "string"
},
"progressPercent": {
"description": "Approximate percentage processed thus far. Guaranteed to be\n100 when fully processed.",
"format": "int32",
"type": "integer"
},
"segment": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment",
"description": "Specifies which segment is being tracked if the request contains more than\none segments."
},
"startTime": {
"description": "Time when the request was received.",
"format": "google-datetime",
"type": "string"
},
"updateTime": {
"description": "Time of the most recent update.",
"format": "google-datetime",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationResults": {
"description": "Annotation results for a single video.",
"id": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationResults",
"properties": {
"error": {
"$ref": "GoogleRpc_Status",
"description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest`\nsome videos may succeed and some may fail."
},
"explicitAnnotation": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentAnnotation",
"description": "Explicit content annotation."
},
"frameLabelAnnotations": {
"description": "Label annotations on frame level.\nThere is exactly one element for each unique label.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation"
},
"type": "array"
},
"inputUri": {
"description": "Video file location in\n[Cloud Storage](https://cloud.google.com/storage/).",
"type": "string"
},
"objectAnnotations": {
"description": "Annotations for list of objects detected and tracked in video.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingAnnotation"
},
"type": "array"
},
"segment": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment",
"description": "Video segment on which the annotation is run."
},
"segmentLabelAnnotations": {
"description": "Topical label annotations on video level or user specified segment level.\nThere is exactly one element for each unique label.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation"
},
"type": "array"
},
"segmentPresenceLabelAnnotations": {
"description": "Presence label annotations on video level or user specified segment level.\nThere is exactly one element for each unique label. Compared to the\nexisting topical `segment_label_annotations`, this field presents more\nfine-grained, segment-level labels detected in video content and is made\navailable only when the client sets `LabelDetectionConfig.model` to\n\"builtin/latest\" in the request.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation"
},
"type": "array"
},
"shotAnnotations": {
"description": "Shot annotations. Each shot is represented as a video segment.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment"
},
"type": "array"
},
"shotLabelAnnotations": {
"description": "Topical label annotations on shot level.\nThere is exactly one element for each unique label.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation"
},
"type": "array"
},
"shotPresenceLabelAnnotations": {
"description": "Presence label annotations on shot level. There is exactly one element for\neach unique label. Compared to the existing topical\n`shot_label_annotations`, this field presents more fine-grained, shot-level\nlabels detected in video content and is made available only when the client\nsets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation"
},
"type": "array"
},
"speechTranscriptions": {
"description": "Speech transcription.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscription"
},
"type": "array"
},
"textAnnotations": {
"description": "OCR text detection and tracking.\nAnnotations for list of detected text snippets. Each will have list of\nframe information associated with it.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p1beta1_TextAnnotation"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p1beta1_VideoSegment": {
"description": "Video segment.",
"id": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment",
"properties": {
"endTimeOffset": {
"description": "Time-offset, relative to the beginning of the video,\ncorresponding to the end of the segment (inclusive).",
"format": "google-duration",
"type": "string"
},
"startTimeOffset": {
"description": "Time-offset, relative to the beginning of the video,\ncorresponding to the start of the segment (inclusive).",
"format": "google-duration",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p1beta1_WordInfo": {
"description": "Word-specific information for recognized words. Word information is only\nincluded in the response when certain request parameters are set, such\nas `enable_word_time_offsets`.",
"id": "GoogleCloudVideointelligenceV1p1beta1_WordInfo",
"properties": {
"confidence": {
"description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number\nindicates an estimated greater likelihood that the recognized words are\ncorrect. This field is set only for the top alternative.\nThis field is not guaranteed to be accurate and users should not rely on it\nto be always provided.\nThe default of 0.0 is a sentinel value indicating `confidence` was not set.",
"format": "float",
"type": "number"
},
"endTime": {
"description": "Time offset relative to the beginning of the audio, and\ncorresponding to the end of the spoken word. This field is only set if\n`enable_word_time_offsets=true` and only in the top hypothesis. This is an\nexperimental 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\nthe audio. This field specifies which one of those speakers was detected to\nhave spoken this word. Value ranges from 1 up to diarization_speaker_count,\nand is only set if speaker diarization is enabled.",
"format": "int32",
"type": "integer"
},
"startTime": {
"description": "Time offset relative to the beginning of the audio, and\ncorresponding to the start of the spoken word. This field is only set if\n`enable_word_time_offsets=true` and only in the top hypothesis. This is an\nexperimental 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"
},
"GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoProgress": {
"description": "Video annotation progress. Included in the `metadata`\nfield of the `Operation` returned by the `GetOperation`\ncall of the `google::longrunning::Operations` service.",
"id": "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoProgress",
"properties": {
"annotationProgress": {
"description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationProgress"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoResponse": {
"description": "Video annotation response. Included in the `response`\nfield of the `Operation` returned by the `GetOperation`\ncall of the `google::longrunning::Operations` service.",
"id": "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoResponse",
"properties": {
"annotationResults": {
"description": "Annotation results for all videos specified in `AnnotateVideoRequest`.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationResults"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p2beta1_Entity": {
"description": "Detected entity from video analysis.",
"id": "GoogleCloudVideointelligenceV1p2beta1_Entity",
"properties": {
"description": {
"description": "Textual description, e.g. `Fixed-gear bicycle`.",
"type": "string"
},
"entityId": {
"description": "Opaque entity ID. Some IDs may be available in\n[Google Knowledge Graph Search\nAPI](https://developers.google.com/knowledge-graph/).",
"type": "string"
},
"languageCode": {
"description": "Language code for `description` in BCP-47 format.",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p2beta1_ExplicitContentAnnotation": {
"description": "Explicit content annotation (based on per-frame visual signals only).\nIf no explicit content has been detected in a frame, no annotations are\npresent for that frame.",
"id": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentAnnotation",
"properties": {
"frames": {
"description": "All video frames where explicit content was detected.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentFrame"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p2beta1_ExplicitContentFrame": {
"description": "Video frame level annotation results for explicit content.",
"id": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentFrame",
"properties": {
"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"
},
"timeOffset": {
"description": "Time-offset, relative to the beginning of the video, corresponding to the\nvideo frame for this location.",
"format": "google-duration",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation": {
"description": "Label annotation.",
"id": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation",
"properties": {
"categoryEntities": {
"description": "Common categories for the detected entity.\nE.g. when the label is `Terrier` the category is likely `dog`. And in some\ncases there might be more than one categories e.g. `Terrier` could also be\na `pet`.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity"
},
"type": "array"
},
"entity": {
"$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity",
"description": "Detected entity."
},
"frames": {
"description": "All video frames where a label was detected.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelFrame"
},
"type": "array"
},
"segments": {
"description": "All video segments where a label was detected.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelSegment"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p2beta1_LabelFrame": {
"description": "Video frame level annotation results for label detection.",
"id": "GoogleCloudVideointelligenceV1p2beta1_LabelFrame",
"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\nvideo frame for this location.",
"format": "google-duration",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p2beta1_LabelSegment": {
"description": "Video segment level annotation results for label detection.",
"id": "GoogleCloudVideointelligenceV1p2beta1_LabelSegment",
"properties": {
"confidence": {
"description": "Confidence that the label is accurate. Range: [0, 1].",
"format": "float",
"type": "number"
},
"segment": {
"$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment",
"description": "Video segment where a label was detected."
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox": {
"description": "Normalized bounding box.\nThe normalized vertex coordinates are relative to the original image.\nRange: [0, 1].",
"id": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox",
"properties": {
"bottom": {
"description": "Bottom Y coordinate.",
"format": "float",
"type": "number"
},
"left": {
"description": "Left X coordinate.",
"format": "float",
"type": "number"
},
"right": {
"description": "Right X coordinate.",
"format": "float",
"type": "number"
},
"top": {
"description": "Top Y coordinate.",
"format": "float",
"type": "number"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingPoly": {
"description": "Normalized bounding polygon for text (that might not be aligned with axis).\nContains list of the corner points in clockwise order starting from\ntop-left corner. For example, for a rectangular bounding box:\nWhen the text is horizontal it might look like:\n 0----1\n | |\n 3----2\n\nWhen it's clockwise rotated 180 degrees around the top-left corner it\nbecomes:\n 2----3\n | |\n 1----0\n\nand the vertex order will still be (0, 1, 2, 3). Note that values can be less\nthan 0, or greater than 1 due to trignometric calculations for location of\nthe box.",
"id": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingPoly",
"properties": {
"vertices": {
"description": "Normalized vertices of the bounding polygon.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex": {
"description": "A vertex represents a 2D point in the image.\nNOTE: the normalized vertex coordinates are relative to the original image\nand range from 0 to 1.",
"id": "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex",
"properties": {
"x": {
"description": "X coordinate.",
"format": "float",
"type": "number"
},
"y": {
"description": "Y coordinate.",
"format": "float",
"type": "number"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingAnnotation": {
"description": "Annotations corresponding to one tracked object.",
"id": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingAnnotation",
"properties": {
"confidence": {
"description": "Object category's labeling confidence of this track.",
"format": "float",
"type": "number"
},
"entity": {
"$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity",
"description": "Entity to specify the object category that this track is labeled as."
},
"frames": {
"description": "Information corresponding to all frames where this object track appears.\nNon-streaming batch mode: it may be one or multiple ObjectTrackingFrame\nmessages in frames.\nStreaming mode: it can only be one ObjectTrackingFrame message in frames.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingFrame"
},
"type": "array"
},
"segment": {
"$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment",
"description": "Non-streaming batch mode ONLY.\nEach object track corresponds to one video segment where it appears."
},
"trackId": {
"description": "Streaming mode ONLY.\nIn streaming mode, we do not know the end time of a tracked object\nbefore it is completed. Hence, there is no VideoSegment info returned.\nInstead, we provide a unique identifiable integer track_id so that\nthe customers can correlate the results of the ongoing\nObjectTrackAnnotation of the same track_id over time.",
"format": "int64",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingFrame": {
"description": "Video frame level annotations for object detection and tracking. This field\nstores per frame location, time offset, and confidence.",
"id": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingFrame",
"properties": {
"normalizedBoundingBox": {
"$ref": "GoogleCloudVideointelligenceV1p2beta1_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"
},
"GoogleCloudVideointelligenceV1p2beta1_SpeechRecognitionAlternative": {
"description": "Alternative hypotheses (a.k.a. n-best list).",
"id": "GoogleCloudVideointelligenceV1p2beta1_SpeechRecognitionAlternative",
"properties": {
"confidence": {
"description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number\nindicates an estimated greater likelihood that the recognized words are\ncorrect. This field is set only for the top alternative.\nThis field is not guaranteed to be accurate and users should not rely on it\nto be always provided.\nThe default of 0.0 is a sentinel value indicating `confidence` was not set.",
"format": "float",
"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.\nNote: When `enable_speaker_diarization` is true, you will see all the words\nfrom the beginning of the audio.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p2beta1_WordInfo"
},
"type": "array"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p2beta1_SpeechTranscription": {
"description": "A speech recognition result corresponding to a portion of the audio.",
"id": "GoogleCloudVideointelligenceV1p2beta1_SpeechTranscription",
"properties": {
"alternatives": {
"description": "May contain one or more recognition hypotheses (up to the maximum specified\nin `max_alternatives`). These alternatives are ordered in terms of\naccuracy, with the top (first) alternative being the most probable, as\nranked by the recognizer.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p2beta1_SpeechRecognitionAlternative"
},
"type": "array"
},
"languageCode": {
"description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of\nthe language in this result. This language code was detected to have the\nmost likelihood of being spoken in the audio.",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p2beta1_TextAnnotation": {
"description": "Annotations related to one detected OCR text snippet. This will contain the\ncorresponding text, confidence value, and frame level information for each\ndetection.",
"id": "GoogleCloudVideointelligenceV1p2beta1_TextAnnotation",
"properties": {
"segments": {
"description": "All video segments where OCR detected text appears.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p2beta1_TextSegment"
},
"type": "array"
},
"text": {
"description": "The detected text.",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p2beta1_TextFrame": {
"description": "Video frame level annotation results for text annotation (OCR).\nContains information regarding timestamp and bounding box locations for the\nframes containing detected OCR text snippets.",
"id": "GoogleCloudVideointelligenceV1p2beta1_TextFrame",
"properties": {
"rotatedBoundingBox": {
"$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingPoly",
"description": "Bounding polygon of the detected text for this frame."
},
"timeOffset": {
"description": "Timestamp of this frame.",
"format": "google-duration",
"type": "string"
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p2beta1_TextSegment": {
"description": "Video segment level annotation results for text detection.",
"id": "GoogleCloudVideointelligenceV1p2beta1_TextSegment",
"properties": {
"confidence": {
"description": "Confidence for the track of detected text. It is calculated as the highest\nover all frames where OCR detected text appears.",
"format": "float",
"type": "number"
},
"frames": {
"description": "Information related to the frames where OCR detected text appears.",
"items": {
"$ref": "GoogleCloudVideointelligenceV1p2beta1_TextFrame"
},
"type": "array"
},
"segment": {
"$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment",
"description": "Video segment where a text snippet was detected."
}
},
"type": "object"
},
"GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationProgress": {
"description": "Annotation progress for a single video.",
"id": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationProgress",
"properties": {
"feature": {
"description": "Specifies which feature is being tracked if the request contains more than\none features.",
"enum": [
"FEATURE_UNSPECIFIED",
"LABEL_DETECTION",
"SHOT_CHANGE_DETECTION",
"EXPLICIT_CONTENT_DETECTION",
"SPEECH_TRANSCRIPTION",
"TEXT_DETECTION",
"OBJECT_TRACKING"
],
"enumDescriptions": [
"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."
],
"type": "string"
},
"inputUri": {
"description": "Video file location in\n[Cloud Storage](https://cloud.google.com/storage/).",
"type": "string"
},
"progressPercent": {
"description": "Approximate percentage processed thus far. Guaranteed to be\n100 when fully processed.",
"format": "int32",
"type": "integer"
},
"segment": {
"$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment",
"description": "Specifies which segment is being tracked if the request contains more than\none segments."
},
"startTime": {
"description": "Time when the request was received.",
"format": "google-datetime",
"type": "string"
},
"updateTime": {