push all website files

website/functions/node_modules/google-proto-files/google/cloud/videointelligence/v1/video_intelligence.proto

@@ -0,0 +1,392 @@
+// Copyright 2017 Google Inc.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+syntax = "proto3";
+
+package google.cloud.videointelligence.v1;
+
+import "google/api/annotations.proto";
+import "google/longrunning/operations.proto";
+import "google/protobuf/duration.proto";
+import "google/protobuf/timestamp.proto";
+import "google/rpc/status.proto";
+
+option csharp_namespace = "Google.Cloud.VideoIntelligence.V1";
+option go_package = "google.golang.org/genproto/googleapis/cloud/videointelligence/v1;videointelligence";
+option java_multiple_files = true;
+option java_outer_classname = "VideoIntelligenceServiceProto";
+option java_package = "com.google.cloud.videointelligence.v1";
+option php_namespace = "Google\\Cloud\\VideoIntelligence\\V1";
+
+
+// Service that implements Google Cloud Video Intelligence API.
+service VideoIntelligenceService {
+  // Performs asynchronous video annotation. Progress and results can be
+  // retrieved through the `google.longrunning.Operations` interface.
+  // `Operation.metadata` contains `AnnotateVideoProgress` (progress).
+  // `Operation.response` contains `AnnotateVideoResponse` (results).
+  rpc AnnotateVideo(AnnotateVideoRequest) returns (google.longrunning.Operation) {
+    option (google.api.http) = { post: "/v1/videos:annotate" body: "*" };
+  }
+}
+
+// Video annotation request.
+message AnnotateVideoRequest {
+  // Input video location. Currently, only
+  // [Google Cloud Storage](https://cloud.google.com/storage/) URIs are
+  // supported, which must be specified in the following format:
+  // `gs://bucket-id/object-id` (other URI formats return
+  // [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see
+  // [Request URIs](/storage/docs/reference-uris).
+  // A video URI may include wildcards in `object-id`, and thus identify
+  // multiple videos. Supported wildcards: '*' to match 0 or more characters;
+  // '?' to match 1 character. If unset, the input video should be embedded
+  // in the request as `input_content`. If set, `input_content` should be unset.
+  string input_uri = 1;
+
+  // The video data bytes.
+  // If unset, the input video(s) should be specified via `input_uri`.
+  // If set, `input_uri` should be unset.
+  bytes input_content = 6;
+
+  // Requested video annotation features.
+  repeated Feature features = 2;
+
+  // Additional video context and/or feature-specific parameters.
+  VideoContext video_context = 3;
+
+  // Optional location where the output (in JSON format) should be stored.
+  // Currently, only [Google Cloud Storage](https://cloud.google.com/storage/)
+  // URIs are supported, which must be specified in the following format:
+  // `gs://bucket-id/object-id` (other URI formats return
+  // [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see
+  // [Request URIs](/storage/docs/reference-uris).
+  string output_uri = 4;
+
+  // Optional cloud region where annotation should take place. Supported cloud
+  // regions: `us-east1`, `us-west1`, `europe-west1`, `asia-east1`. If no region
+  // is specified, a region will be determined based on video file location.
+  string location_id = 5;
+}
+
+// Video context and/or feature-specific parameters.
+message VideoContext {
+  // Video segments to annotate. The segments may overlap and are not required
+  // to be contiguous or span the whole video. If unspecified, each video
+  // is treated as a single segment.
+  repeated VideoSegment segments = 1;
+
+  // Config for LABEL_DETECTION.
+  LabelDetectionConfig label_detection_config = 2;
+
+  // Config for SHOT_CHANGE_DETECTION.
+  ShotChangeDetectionConfig shot_change_detection_config = 3;
+
+  // Config for EXPLICIT_CONTENT_DETECTION.
+  ExplicitContentDetectionConfig explicit_content_detection_config = 4;
+
+  // Config for FACE_DETECTION.
+  FaceDetectionConfig face_detection_config = 5;
+}
+
+// Config for LABEL_DETECTION.
+message LabelDetectionConfig {
+  // What labels should be detected with LABEL_DETECTION, in addition to
+  // video-level labels or segment-level labels.
+  // If unspecified, defaults to `SHOT_MODE`.
+  LabelDetectionMode label_detection_mode = 1;
+
+  // Whether the video has been shot from a stationary (i.e. non-moving) camera.
+  // When set to true, might improve detection accuracy for moving objects.
+  // Should be used with `SHOT_AND_FRAME_MODE` enabled.
+  bool stationary_camera = 2;
+
+  // Model to use for label detection.
+  // Supported values: "builtin/stable" (the default if unset) and
+  // "builtin/latest".
+  string model = 3;
+}
+
+// Config for SHOT_CHANGE_DETECTION.
+message ShotChangeDetectionConfig {
+  // Model to use for shot change detection.
+  // Supported values: "builtin/stable" (the default if unset) and
+  // "builtin/latest".
+  string model = 1;
+}
+
+// Config for EXPLICIT_CONTENT_DETECTION.
+message ExplicitContentDetectionConfig {
+  // Model to use for explicit content detection.
+  // Supported values: "builtin/stable" (the default if unset) and
+  // "builtin/latest".
+  string model = 1;
+}
+
+// Config for FACE_DETECTION.
+message FaceDetectionConfig {
+  // Model to use for face detection.
+  // Supported values: "builtin/stable" (the default if unset) and
+  // "builtin/latest".
+  string model = 1;
+
+  // Whether bounding boxes be included in the face annotation output.
+  bool include_bounding_boxes = 2;
+}
+
+// Video segment.
+message VideoSegment {
+  // Time-offset, relative to the beginning of the video,
+  // corresponding to the start of the segment (inclusive).
+  google.protobuf.Duration start_time_offset = 1;
+
+  // Time-offset, relative to the beginning of the video,
+  // corresponding to the end of the segment (inclusive).
+  google.protobuf.Duration end_time_offset = 2;
+}
+
+// Video segment level annotation results for label detection.
+message LabelSegment {
+  // Video segment where a label was detected.
+  VideoSegment segment = 1;
+
+  // Confidence that the label is accurate. Range: [0, 1].
+  float confidence = 2;
+}
+
+// Video frame level annotation results for label detection.
+message LabelFrame {
+  // Time-offset, relative to the beginning of the video, corresponding to the
+  // video frame for this location.
+  google.protobuf.Duration time_offset = 1;
+
+  // Confidence that the label is accurate. Range: [0, 1].
+  float confidence = 2;
+}
+
+// Detected entity from video analysis.
+message Entity {
+  // Opaque entity ID. Some IDs may be available in
+  // [Google Knowledge Graph Search
+  // API](https://developers.google.com/knowledge-graph/).
+  string entity_id = 1;
+
+  // Textual description, e.g. `Fixed-gear bicycle`.
+  string description = 2;
+
+  // Language code for `description` in BCP-47 format.
+  string language_code = 3;
+}
+
+// Label annotation.
+message LabelAnnotation {
+  // Detected entity.
+  Entity entity = 1;
+
+  // Common categories for the detected entity.
+  // E.g. when the label is `Terrier` the category is likely `dog`. And in some
+  // cases there might be more than one categories e.g. `Terrier` could also be
+  // a `pet`.
+  repeated Entity category_entities = 2;
+
+  // All video segments where a label was detected.
+  repeated LabelSegment segments = 3;
+
+  // All video frames where a label was detected.
+  repeated LabelFrame frames = 4;
+}
+
+// Video frame level annotation results for explicit content.
+message ExplicitContentFrame {
+  // Time-offset, relative to the beginning of the video, corresponding to the
+  // video frame for this location.
+  google.protobuf.Duration time_offset = 1;
+
+  // Likelihood of the pornography content..
+  Likelihood pornography_likelihood = 2;
+}
+
+// Explicit content annotation (based on per-frame visual signals only).
+// If no explicit content has been detected in a frame, no annotations are
+// present for that frame.
+message ExplicitContentAnnotation {
+  // All video frames where explicit content was detected.
+  repeated ExplicitContentFrame frames = 1;
+}
+
+// Normalized bounding box.
+// The normalized vertex coordinates are relative to the original image.
+// Range: [0, 1].
+message NormalizedBoundingBox {
+  // Left X coordinate.
+  float left = 1;
+
+  // Top Y coordinate.
+  float top = 2;
+
+  // Right X coordinate.
+  float right = 3;
+
+  // Bottom Y coordinate.
+  float bottom = 4;
+}
+
+// Video segment level annotation results for face detection.
+message FaceSegment {
+  // Video segment where a face was detected.
+  VideoSegment segment = 1;
+}
+
+// Video frame level annotation results for face detection.
+message FaceFrame {
+  // Normalized Bounding boxes in a frame.
+  // There can be more than one boxes if the same face is detected in multiple
+  // locations within the current frame.
+  repeated NormalizedBoundingBox normalized_bounding_boxes = 1;
+
+  // Time-offset, relative to the beginning of the video,
+  // corresponding to the video frame for this location.
+  google.protobuf.Duration time_offset = 2;
+}
+
+// Face annotation.
+message FaceAnnotation {
+  // Thumbnail of a representative face view (in JPEG format).
+  bytes thumbnail = 1;
+
+  // All video segments where a face was detected.
+  repeated FaceSegment segments = 2;
+
+  // All video frames where a face was detected.
+  repeated FaceFrame frames = 3;
+}
+
+// Annotation results for a single video.
+message VideoAnnotationResults {
+  // Video file location in
+  // [Google Cloud Storage](https://cloud.google.com/storage/).
+  string input_uri = 1;
+
+  // Label annotations on video level or user specified segment level.
+  // There is exactly one element for each unique label.
+  repeated LabelAnnotation segment_label_annotations = 2;
+
+  // Label annotations on shot level.
+  // There is exactly one element for each unique label.
+  repeated LabelAnnotation shot_label_annotations = 3;
+
+  // Label annotations on frame level.
+  // There is exactly one element for each unique label.
+  repeated LabelAnnotation frame_label_annotations = 4;
+
+  // Face annotations. There is exactly one element for each unique face.
+  repeated FaceAnnotation face_annotations = 5;
+
+  // Shot annotations. Each shot is represented as a video segment.
+  repeated VideoSegment shot_annotations = 6;
+
+  // Explicit content annotation.
+  ExplicitContentAnnotation explicit_annotation = 7;
+
+  // If set, indicates an error. Note that for a single `AnnotateVideoRequest`
+  // some videos may succeed and some may fail.
+  google.rpc.Status error = 9;
+}
+
+// Video annotation response. Included in the `response`
+// field of the `Operation` returned by the `GetOperation`
+// call of the `google::longrunning::Operations` service.
+message AnnotateVideoResponse {
+  // Annotation results for all videos specified in `AnnotateVideoRequest`.
+  repeated VideoAnnotationResults annotation_results = 1;
+}
+
+// Annotation progress for a single video.
+message VideoAnnotationProgress {
+  // Video file location in
+  // [Google Cloud Storage](https://cloud.google.com/storage/).
+  string input_uri = 1;
+
+  // Approximate percentage processed thus far.
+  // Guaranteed to be 100 when fully processed.
+  int32 progress_percent = 2;
+
+  // Time when the request was received.
+  google.protobuf.Timestamp start_time = 3;
+
+  // Time of the most recent update.
+  google.protobuf.Timestamp update_time = 4;
+}
+
+// Video annotation progress. Included in the `metadata`
+// field of the `Operation` returned by the `GetOperation`
+// call of the `google::longrunning::Operations` service.
+message AnnotateVideoProgress {
+  // Progress metadata for all videos specified in `AnnotateVideoRequest`.
+  repeated VideoAnnotationProgress annotation_progress = 1;
+}
+
+// Video annotation feature.
+enum Feature {
+  // Unspecified.
+  FEATURE_UNSPECIFIED = 0;
+
+  // Label detection. Detect objects, such as dog or flower.
+  LABEL_DETECTION = 1;
+
+  // Shot change detection.
+  SHOT_CHANGE_DETECTION = 2;
+
+  // Explicit content detection.
+  EXPLICIT_CONTENT_DETECTION = 3;
+
+  // Human face detection and tracking.
+  FACE_DETECTION = 4;
+}
+
+// Label detection mode.
+enum LabelDetectionMode {
+  // Unspecified.
+  LABEL_DETECTION_MODE_UNSPECIFIED = 0;
+
+  // Detect shot-level labels.
+  SHOT_MODE = 1;
+
+  // Detect frame-level labels.
+  FRAME_MODE = 2;
+
+  // Detect both shot-level and frame-level labels.
+  SHOT_AND_FRAME_MODE = 3;
+}
+
+// Bucketized representation of likelihood.
+enum Likelihood {
+  // Unspecified likelihood.
+  LIKELIHOOD_UNSPECIFIED = 0;
+
+  // Very unlikely.
+  VERY_UNLIKELY = 1;
+
+  // Unlikely.
+  UNLIKELY = 2;
+
+  // Possible.
+  POSSIBLE = 3;
+
+  // Likely.
+  LIKELY = 4;
+
+  // Very likely.
+  VERY_LIKELY = 5;
+}

website/functions/node_modules/google-proto-files/google/cloud/videointelligence/v1beta1/video_intelligence.proto

@@ -0,0 +1,340 @@
+// Copyright 2017 Google Inc.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+syntax = "proto3";
+
+package google.cloud.videointelligence.v1beta1;
+
+import "google/api/annotations.proto";
+import "google/longrunning/operations.proto";
+import "google/protobuf/timestamp.proto";
+import "google/rpc/status.proto";
+
+option csharp_namespace = "Google.Cloud.VideoIntelligence.V1Beta1";
+option go_package = "google.golang.org/genproto/googleapis/cloud/videointelligence/v1beta1;videointelligence";
+option java_multiple_files = true;
+option java_outer_classname = "VideoIntelligenceServiceProto";
+option java_package = "com.google.cloud.videointelligence.v1beta1";
+option php_namespace = "Google\\Cloud\\VideoIntelligence\\V1beta1";
+
+// Service that implements Google Cloud Video Intelligence API.
+service VideoIntelligenceService {
+  // Performs asynchronous video annotation. Progress and results can be
+  // retrieved through the `google.longrunning.Operations` interface.
+  // `Operation.metadata` contains `AnnotateVideoProgress` (progress).
+  // `Operation.response` contains `AnnotateVideoResponse` (results).
+  rpc AnnotateVideo(AnnotateVideoRequest) returns (google.longrunning.Operation) {
+    option (google.api.http) = { post: "/v1beta1/videos:annotate" body: "*" };
+  }
+}
+
+// Video annotation request.
+message AnnotateVideoRequest {
+  // Input video location. Currently, only
+  // [Google Cloud Storage](https://cloud.google.com/storage/) URIs are
+  // supported, which must be specified in the following format:
+  // `gs://bucket-id/object-id` (other URI formats return
+  // [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see
+  // [Request URIs](/storage/docs/reference-uris).
+  // A video URI may include wildcards in `object-id`, and thus identify
+  // multiple videos. Supported wildcards: '*' to match 0 or more characters;
+  // '?' to match 1 character. If unset, the input video should be embedded
+  // in the request as `input_content`. If set, `input_content` should be unset.
+  string input_uri = 1;
+
+  // The video data bytes. Encoding: base64. If unset, the input video(s)
+  // should be specified via `input_uri`. If set, `input_uri` should be unset.
+  string input_content = 6;
+
+  // Requested video annotation features.
+  repeated Feature features = 2;
+
+  // Additional video context and/or feature-specific parameters.
+  VideoContext video_context = 3;
+
+  // Optional location where the output (in JSON format) should be stored.
+  // Currently, only [Google Cloud Storage](https://cloud.google.com/storage/)
+  // URIs are supported, which must be specified in the following format:
+  // `gs://bucket-id/object-id` (other URI formats return
+  // [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see
+  // [Request URIs](/storage/docs/reference-uris).
+  string output_uri = 4;
+
+  // Optional cloud region where annotation should take place. Supported cloud
+  // regions: `us-east1`, `us-west1`, `europe-west1`, `asia-east1`. If no region
+  // is specified, a region will be determined based on video file location.
+  string location_id = 5;
+}
+
+// Video context and/or feature-specific parameters.
+message VideoContext {
+  // Video segments to annotate. The segments may overlap and are not required
+  // to be contiguous or span the whole video. If unspecified, each video
+  // is treated as a single segment.
+  repeated VideoSegment segments = 1;
+
+  // If label detection has been requested, what labels should be detected
+  // in addition to video-level labels or segment-level labels. If unspecified,
+  // defaults to `SHOT_MODE`.
+  LabelDetectionMode label_detection_mode = 2;
+
+  // Whether the video has been shot from a stationary (i.e. non-moving) camera.
+  // When set to true, might improve detection accuracy for moving objects.
+  bool stationary_camera = 3;
+
+  // Model to use for label detection.
+  // Supported values: "latest" and "stable" (the default).
+  string label_detection_model = 4;
+
+  // Model to use for face detection.
+  // Supported values: "latest" and "stable" (the default).
+  string face_detection_model = 5;
+
+  // Model to use for shot change detection.
+  // Supported values: "latest" and "stable" (the default).
+  string shot_change_detection_model = 6;
+
+  // Model to use for safe search detection.
+  // Supported values: "latest" and "stable" (the default).
+  string safe_search_detection_model = 7;
+}
+
+// Video segment.
+message VideoSegment {
+  // Start offset in microseconds (inclusive). Unset means 0.
+  int64 start_time_offset = 1;
+
+  // End offset in microseconds (inclusive). Unset means 0.
+  int64 end_time_offset = 2;
+}
+
+// Label location.
+message LabelLocation {
+  // Video segment. Set to [-1, -1] for video-level labels.
+  // Set to [timestamp, timestamp] for frame-level labels.
+  // Otherwise, corresponds to one of `AnnotateSpec.segments`
+  // (if specified) or to shot boundaries (if requested).
+  VideoSegment segment = 1;
+
+  // Confidence that the label is accurate. Range: [0, 1].
+  float confidence = 2;
+
+  // Label level.
+  LabelLevel level = 3;
+}
+
+// Label annotation.
+message LabelAnnotation {
+  // Textual description, e.g. `Fixed-gear bicycle`.
+  string description = 1;
+
+  // Language code for `description` in BCP-47 format.
+  string language_code = 2;
+
+  // Where the label was detected and with what confidence.
+  repeated LabelLocation locations = 3;
+}
+
+// Safe search annotation (based on per-frame visual signals only).
+// If no unsafe content has been detected in a frame, no annotations
+// are present for that frame. If only some types of unsafe content
+// have been detected in a frame, the likelihood is set to `UNKNOWN`
+// for all other types of unsafe content.
+message SafeSearchAnnotation {
+  // Likelihood of adult content.
+  Likelihood adult = 1;
+
+  // Likelihood that an obvious modification was made to the original
+  // version to make it appear funny or offensive.
+  Likelihood spoof = 2;
+
+  // Likelihood of medical content.
+  Likelihood medical = 3;
+
+  // Likelihood of violent content.
+  Likelihood violent = 4;
+
+  // Likelihood of racy content.
+  Likelihood racy = 5;
+
+  // Video time offset in microseconds.
+  int64 time_offset = 6;
+}
+
+// Bounding box.
+message BoundingBox {
+  // Left X coordinate.
+  int32 left = 1;
+
+  // Right X coordinate.
+  int32 right = 2;
+
+  // Bottom Y coordinate.
+  int32 bottom = 3;
+
+  // Top Y coordinate.
+  int32 top = 4;
+}
+
+// Face location.
+message FaceLocation {
+  // Bounding box in a frame.
+  BoundingBox bounding_box = 1;
+
+  // Video time offset in microseconds.
+  int64 time_offset = 2;
+}
+
+// Face annotation.
+message FaceAnnotation {
+  // Thumbnail of a representative face view (in JPEG format). Encoding: base64.
+  string thumbnail = 1;
+
+  // All locations where a face was detected.
+  // Faces are detected and tracked on a per-video basis
+  // (as opposed to across multiple videos).
+  repeated VideoSegment segments = 2;
+
+  // Face locations at one frame per second.
+  repeated FaceLocation locations = 3;
+}
+
+// Annotation results for a single video.
+message VideoAnnotationResults {
+  // Video file location in
+  // [Google Cloud Storage](https://cloud.google.com/storage/).
+  string input_uri = 1;
+
+  // Label annotations. There is exactly one element for each unique label.
+  repeated LabelAnnotation label_annotations = 2;
+
+  // Face annotations. There is exactly one element for each unique face.
+  repeated FaceAnnotation face_annotations = 3;
+
+  // Shot annotations. Each shot is represented as a video segment.
+  repeated VideoSegment shot_annotations = 4;
+
+  // Safe search annotations.
+  repeated SafeSearchAnnotation safe_search_annotations = 6;
+
+  // If set, indicates an error. Note that for a single `AnnotateVideoRequest`
+  // some videos may succeed and some may fail.
+  google.rpc.Status error = 5;
+}
+
+// Video annotation response. Included in the `response`
+// field of the `Operation` returned by the `GetOperation`
+// call of the `google::longrunning::Operations` service.
+message AnnotateVideoResponse {
+  // Annotation results for all videos specified in `AnnotateVideoRequest`.
+  repeated VideoAnnotationResults annotation_results = 1;
+}
+
+// Annotation progress for a single video.
+message VideoAnnotationProgress {
+  // Video file location in
+  // [Google Cloud Storage](https://cloud.google.com/storage/).
+  string input_uri = 1;
+
+  // Approximate percentage processed thus far.
+  // Guaranteed to be 100 when fully processed.
+  int32 progress_percent = 2;
+
+  // Time when the request was received.
+  google.protobuf.Timestamp start_time = 3;
+
+  // Time of the most recent update.
+  google.protobuf.Timestamp update_time = 4;
+}
+
+// Video annotation progress. Included in the `metadata`
+// field of the `Operation` returned by the `GetOperation`
+// call of the `google::longrunning::Operations` service.
+message AnnotateVideoProgress {
+  // Progress metadata for all videos specified in `AnnotateVideoRequest`.
+  repeated VideoAnnotationProgress annotation_progress = 1;
+}
+
+// Video annotation feature.
+enum Feature {
+  // Unspecified.
+  FEATURE_UNSPECIFIED = 0;
+
+  // Label detection. Detect objects, such as dog or flower.
+  LABEL_DETECTION = 1;
+
+  // Human face detection and tracking.
+  FACE_DETECTION = 2;
+
+  // Shot change detection.
+  SHOT_CHANGE_DETECTION = 3;
+
+  // Safe search detection.
+  SAFE_SEARCH_DETECTION = 4;
+}
+
+// Label level (scope).
+enum LabelLevel {
+  // Unspecified.
+  LABEL_LEVEL_UNSPECIFIED = 0;
+
+  // Video-level. Corresponds to the whole video.
+  VIDEO_LEVEL = 1;
+
+  // Segment-level. Corresponds to one of `AnnotateSpec.segments`.
+  SEGMENT_LEVEL = 2;
+
+  // Shot-level. Corresponds to a single shot (i.e. a series of frames
+  // without a major camera position or background change).
+  SHOT_LEVEL = 3;
+
+  // Frame-level. Corresponds to a single video frame.
+  FRAME_LEVEL = 4;
+}
+
+// Label detection mode.
+enum LabelDetectionMode {
+  // Unspecified.
+  LABEL_DETECTION_MODE_UNSPECIFIED = 0;
+
+  // Detect shot-level labels.
+  SHOT_MODE = 1;
+
+  // Detect frame-level labels.
+  FRAME_MODE = 2;
+
+  // Detect both shot-level and frame-level labels.
+  SHOT_AND_FRAME_MODE = 3;
+}
+
+// Bucketized representation of likelihood.
+enum Likelihood {
+  // Unknown likelihood.
+  UNKNOWN = 0;
+
+  // Very unlikely.
+  VERY_UNLIKELY = 1;
+
+  // Unlikely.
+  UNLIKELY = 2;
+
+  // Possible.
+  POSSIBLE = 3;
+
+  // Likely.
+  LIKELY = 4;
+
+  // Very likely.
+  VERY_LIKELY = 5;
+}

website/functions/node_modules/google-proto-files/google/cloud/videointelligence/v1beta2/video_intelligence.proto

@@ -0,0 +1,392 @@
+// Copyright 2017 Google Inc.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+syntax = "proto3";
+
+package google.cloud.videointelligence.v1beta2;
+
+import "google/api/annotations.proto";
+import "google/longrunning/operations.proto";
+import "google/protobuf/duration.proto";
+import "google/protobuf/timestamp.proto";
+import "google/rpc/status.proto";
+
+option csharp_namespace = "Google.Cloud.VideoIntelligence.V1Beta2";
+option go_package = "google.golang.org/genproto/googleapis/cloud/videointelligence/v1beta2;videointelligence";
+option java_multiple_files = true;
+option java_outer_classname = "VideoIntelligenceServiceProto";
+option java_package = "com.google.cloud.videointelligence.v1beta2";
+option php_namespace = "Google\\Cloud\\VideoIntelligence\\V1beta2";
+
+
+// Service that implements Google Cloud Video Intelligence API.
+service VideoIntelligenceService {
+  // Performs asynchronous video annotation. Progress and results can be
+  // retrieved through the `google.longrunning.Operations` interface.
+  // `Operation.metadata` contains `AnnotateVideoProgress` (progress).
+  // `Operation.response` contains `AnnotateVideoResponse` (results).
+  rpc AnnotateVideo(AnnotateVideoRequest) returns (google.longrunning.Operation) {
+    option (google.api.http) = { post: "/v1beta2/videos:annotate" body: "*" };
+  }
+}
+
+// Video annotation request.
+message AnnotateVideoRequest {
+  // Input video location. Currently, only
+  // [Google Cloud Storage](https://cloud.google.com/storage/) URIs are
+  // supported, which must be specified in the following format:
+  // `gs://bucket-id/object-id` (other URI formats return
+  // [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see
+  // [Request URIs](/storage/docs/reference-uris).
+  // A video URI may include wildcards in `object-id`, and thus identify
+  // multiple videos. Supported wildcards: '*' to match 0 or more characters;
+  // '?' to match 1 character. If unset, the input video should be embedded
+  // in the request as `input_content`. If set, `input_content` should be unset.
+  string input_uri = 1;
+
+  // The video data bytes.
+  // If unset, the input video(s) should be specified via `input_uri`.
+  // If set, `input_uri` should be unset.
+  bytes input_content = 6;
+
+  // Requested video annotation features.
+  repeated Feature features = 2;
+
+  // Additional video context and/or feature-specific parameters.
+  VideoContext video_context = 3;
+
+  // Optional location where the output (in JSON format) should be stored.
+  // Currently, only [Google Cloud Storage](https://cloud.google.com/storage/)
+  // URIs are supported, which must be specified in the following format:
+  // `gs://bucket-id/object-id` (other URI formats return
+  // [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see
+  // [Request URIs](/storage/docs/reference-uris).
+  string output_uri = 4;
+
+  // Optional cloud region where annotation should take place. Supported cloud
+  // regions: `us-east1`, `us-west1`, `europe-west1`, `asia-east1`. If no region
+  // is specified, a region will be determined based on video file location.
+  string location_id = 5;
+}
+
+// Video context and/or feature-specific parameters.
+message VideoContext {
+  // Video segments to annotate. The segments may overlap and are not required
+  // to be contiguous or span the whole video. If unspecified, each video
+  // is treated as a single segment.
+  repeated VideoSegment segments = 1;
+
+  // Config for LABEL_DETECTION.
+  LabelDetectionConfig label_detection_config = 2;
+
+  // Config for SHOT_CHANGE_DETECTION.
+  ShotChangeDetectionConfig shot_change_detection_config = 3;
+
+  // Config for EXPLICIT_CONTENT_DETECTION.
+  ExplicitContentDetectionConfig explicit_content_detection_config = 4;
+
+  // Config for FACE_DETECTION.
+  FaceDetectionConfig face_detection_config = 5;
+}
+
+// Config for LABEL_DETECTION.
+message LabelDetectionConfig {
+  // What labels should be detected with LABEL_DETECTION, in addition to
+  // video-level labels or segment-level labels.
+  // If unspecified, defaults to `SHOT_MODE`.
+  LabelDetectionMode label_detection_mode = 1;
+
+  // Whether the video has been shot from a stationary (i.e. non-moving) camera.
+  // When set to true, might improve detection accuracy for moving objects.
+  // Should be used with `SHOT_AND_FRAME_MODE` enabled.
+  bool stationary_camera = 2;
+
+  // Model to use for label detection.
+  // Supported values: "builtin/stable" (the default if unset) and
+  // "builtin/latest".
+  string model = 3;
+}
+
+// Config for SHOT_CHANGE_DETECTION.
+message ShotChangeDetectionConfig {
+  // Model to use for shot change detection.
+  // Supported values: "builtin/stable" (the default if unset) and
+  // "builtin/latest".
+  string model = 1;
+}
+
+// Config for EXPLICIT_CONTENT_DETECTION.
+message ExplicitContentDetectionConfig {
+  // Model to use for explicit content detection.
+  // Supported values: "builtin/stable" (the default if unset) and
+  // "builtin/latest".
+  string model = 1;
+}
+
+// Config for FACE_DETECTION.
+message FaceDetectionConfig {
+  // Model to use for face detection.
+  // Supported values: "builtin/stable" (the default if unset) and
+  // "builtin/latest".
+  string model = 1;
+
+  // Whether bounding boxes be included in the face annotation output.
+  bool include_bounding_boxes = 2;
+}
+
+// Video segment.
+message VideoSegment {
+  // Time-offset, relative to the beginning of the video,
+  // corresponding to the start of the segment (inclusive).
+  google.protobuf.Duration start_time_offset = 1;
+
+  // Time-offset, relative to the beginning of the video,
+  // corresponding to the end of the segment (inclusive).
+  google.protobuf.Duration end_time_offset = 2;
+}
+
+// Video segment level annotation results for label detection.
+message LabelSegment {
+  // Video segment where a label was detected.
+  VideoSegment segment = 1;
+
+  // Confidence that the label is accurate. Range: [0, 1].
+  float confidence = 2;
+}
+
+// Video frame level annotation results for label detection.
+message LabelFrame {
+  // Time-offset, relative to the beginning of the video, corresponding to the
+  // video frame for this location.
+  google.protobuf.Duration time_offset = 1;
+
+  // Confidence that the label is accurate. Range: [0, 1].
+  float confidence = 2;
+}
+
+// Detected entity from video analysis.
+message Entity {
+  // Opaque entity ID. Some IDs may be available in
+  // [Google Knowledge Graph Search
+  // API](https://developers.google.com/knowledge-graph/).
+  string entity_id = 1;
+
+  // Textual description, e.g. `Fixed-gear bicycle`.
+  string description = 2;
+
+  // Language code for `description` in BCP-47 format.
+  string language_code = 3;
+}
+
+// Label annotation.
+message LabelAnnotation {
+  // Detected entity.
+  Entity entity = 1;
+
+  // Common categories for the detected entity.
+  // E.g. when the label is `Terrier` the category is likely `dog`. And in some
+  // cases there might be more than one categories e.g. `Terrier` could also be
+  // a `pet`.
+  repeated Entity category_entities = 2;
+
+  // All video segments where a label was detected.
+  repeated LabelSegment segments = 3;
+
+  // All video frames where a label was detected.
+  repeated LabelFrame frames = 4;
+}
+
+// Video frame level annotation results for explicit content.
+message ExplicitContentFrame {
+  // Time-offset, relative to the beginning of the video, corresponding to the
+  // video frame for this location.
+  google.protobuf.Duration time_offset = 1;
+
+  // Likelihood of the pornography content..
+  Likelihood pornography_likelihood = 2;
+}
+
+// Explicit content annotation (based on per-frame visual signals only).
+// If no explicit content has been detected in a frame, no annotations are
+// present for that frame.
+message ExplicitContentAnnotation {
+  // All video frames where explicit content was detected.
+  repeated ExplicitContentFrame frames = 1;
+}
+
+// Normalized bounding box.
+// The normalized vertex coordinates are relative to the original image.
+// Range: [0, 1].
+message NormalizedBoundingBox {
+  // Left X coordinate.
+  float left = 1;
+
+  // Top Y coordinate.
+  float top = 2;
+
+  // Right X coordinate.
+  float right = 3;
+
+  // Bottom Y coordinate.
+  float bottom = 4;
+}
+
+// Video segment level annotation results for face detection.
+message FaceSegment {
+  // Video segment where a face was detected.
+  VideoSegment segment = 1;
+}
+
+// Video frame level annotation results for face detection.
+message FaceFrame {
+  // Normalized Bounding boxes in a frame.
+  // There can be more than one boxes if the same face is detected in multiple
+  // locations within the current frame.
+  repeated NormalizedBoundingBox normalized_bounding_boxes = 1;
+
+  // Time-offset, relative to the beginning of the video,
+  // corresponding to the video frame for this location.
+  google.protobuf.Duration time_offset = 2;
+}
+
+// Face annotation.
+message FaceAnnotation {
+  // Thumbnail of a representative face view (in JPEG format).
+  bytes thumbnail = 1;
+
+  // All video segments where a face was detected.
+  repeated FaceSegment segments = 2;
+
+  // All video frames where a face was detected.
+  repeated FaceFrame frames = 3;
+}
+
+// Annotation results for a single video.
+message VideoAnnotationResults {
+  // Video file location in
+  // [Google Cloud Storage](https://cloud.google.com/storage/).
+  string input_uri = 1;
+
+  // Label annotations on video level or user specified segment level.
+  // There is exactly one element for each unique label.
+  repeated LabelAnnotation segment_label_annotations = 2;
+
+  // Label annotations on shot level.
+  // There is exactly one element for each unique label.
+  repeated LabelAnnotation shot_label_annotations = 3;
+
+  // Label annotations on frame level.
+  // There is exactly one element for each unique label.
+  repeated LabelAnnotation frame_label_annotations = 4;
+
+  // Face annotations. There is exactly one element for each unique face.
+  repeated FaceAnnotation face_annotations = 5;
+
+  // Shot annotations. Each shot is represented as a video segment.
+  repeated VideoSegment shot_annotations = 6;
+
+  // Explicit content annotation.
+  ExplicitContentAnnotation explicit_annotation = 7;
+
+  // If set, indicates an error. Note that for a single `AnnotateVideoRequest`
+  // some videos may succeed and some may fail.
+  google.rpc.Status error = 9;
+}
+
+// Video annotation response. Included in the `response`
+// field of the `Operation` returned by the `GetOperation`
+// call of the `google::longrunning::Operations` service.
+message AnnotateVideoResponse {
+  // Annotation results for all videos specified in `AnnotateVideoRequest`.
+  repeated VideoAnnotationResults annotation_results = 1;
+}
+
+// Annotation progress for a single video.
+message VideoAnnotationProgress {
+  // Video file location in
+  // [Google Cloud Storage](https://cloud.google.com/storage/).
+  string input_uri = 1;
+
+  // Approximate percentage processed thus far.
+  // Guaranteed to be 100 when fully processed.
+  int32 progress_percent = 2;
+
+  // Time when the request was received.
+  google.protobuf.Timestamp start_time = 3;
+
+  // Time of the most recent update.
+  google.protobuf.Timestamp update_time = 4;
+}
+
+// Video annotation progress. Included in the `metadata`
+// field of the `Operation` returned by the `GetOperation`
+// call of the `google::longrunning::Operations` service.
+message AnnotateVideoProgress {
+  // Progress metadata for all videos specified in `AnnotateVideoRequest`.
+  repeated VideoAnnotationProgress annotation_progress = 1;
+}
+
+// Video annotation feature.
+enum Feature {
+  // Unspecified.
+  FEATURE_UNSPECIFIED = 0;
+
+  // Label detection. Detect objects, such as dog or flower.
+  LABEL_DETECTION = 1;
+
+  // Shot change detection.
+  SHOT_CHANGE_DETECTION = 2;
+
+  // Explicit content detection.
+  EXPLICIT_CONTENT_DETECTION = 3;
+
+  // Human face detection and tracking.
+  FACE_DETECTION = 4;
+}
+
+// Label detection mode.
+enum LabelDetectionMode {
+  // Unspecified.
+  LABEL_DETECTION_MODE_UNSPECIFIED = 0;
+
+  // Detect shot-level labels.
+  SHOT_MODE = 1;
+
+  // Detect frame-level labels.
+  FRAME_MODE = 2;
+
+  // Detect both shot-level and frame-level labels.
+  SHOT_AND_FRAME_MODE = 3;
+}
+
+// Bucketized representation of likelihood.
+enum Likelihood {
+  // Unspecified likelihood.
+  LIKELIHOOD_UNSPECIFIED = 0;
+
+  // Very unlikely.
+  VERY_UNLIKELY = 1;
+
+  // Unlikely.
+  UNLIKELY = 2;
+
+  // Possible.
+  POSSIBLE = 3;
+
+  // Likely.
+  LIKELY = 4;
+
+  // Very likely.
+  VERY_LIKELY = 5;
+}

website/functions/node_modules/google-proto-files/google/cloud/videointelligence/v1p1beta1/video_intelligence.proto

@@ -0,0 +1,433 @@
+// Copyright 2018 Google Inc.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+syntax = "proto3";
+
+package google.cloud.videointelligence.v1p1beta1;
+
+import "google/api/annotations.proto";
+import "google/longrunning/operations.proto";
+import "google/protobuf/duration.proto";
+import "google/protobuf/timestamp.proto";
+import "google/rpc/status.proto";
+
+option csharp_namespace = "Google.Cloud.VideoIntelligence.V1P1Beta1";
+option go_package = "google.golang.org/genproto/googleapis/cloud/videointelligence/v1p1beta1;videointelligence";
+option java_multiple_files = true;
+option java_outer_classname = "VideoIntelligenceServiceProto";
+option java_package = "com.google.cloud.videointelligence.v1p1beta1";
+option php_namespace = "Google\\Cloud\\VideoIntelligence\\V1p1beta1";
+
+
+// Service that implements Google Cloud Video Intelligence API.
+service VideoIntelligenceService {
+  // Performs asynchronous video annotation. Progress and results can be
+  // retrieved through the `google.longrunning.Operations` interface.
+  // `Operation.metadata` contains `AnnotateVideoProgress` (progress).
+  // `Operation.response` contains `AnnotateVideoResponse` (results).
+  rpc AnnotateVideo(AnnotateVideoRequest) returns (google.longrunning.Operation) {
+    option (google.api.http) = {
+      post: "/v1p1beta1/videos:annotate"
+      body: "*"
+    };
+  }
+}
+
+// Video annotation request.
+message AnnotateVideoRequest {
+  // Input video location. Currently, only
+  // [Google Cloud Storage](https://cloud.google.com/storage/) URIs are
+  // supported, which must be specified in the following format:
+  // `gs://bucket-id/object-id` (other URI formats return
+  // [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see
+  // [Request URIs](/storage/docs/reference-uris).
+  // A video URI may include wildcards in `object-id`, and thus identify
+  // multiple videos. Supported wildcards: '*' to match 0 or more characters;
+  // '?' to match 1 character. If unset, the input video should be embedded
+  // in the request as `input_content`. If set, `input_content` should be unset.
+  string input_uri = 1;
+
+  // The video data bytes.
+  // If unset, the input video(s) should be specified via `input_uri`.
+  // If set, `input_uri` should be unset.
+  bytes input_content = 6;
+
+  // Requested video annotation features.
+  repeated Feature features = 2;
+
+  // Additional video context and/or feature-specific parameters.
+  VideoContext video_context = 3;
+
+  // Optional location where the output (in JSON format) should be stored.
+  // Currently, only [Google Cloud Storage](https://cloud.google.com/storage/)
+  // URIs are supported, which must be specified in the following format:
+  // `gs://bucket-id/object-id` (other URI formats return
+  // [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see
+  // [Request URIs](/storage/docs/reference-uris).
+  string output_uri = 4;
+
+  // Optional cloud region where annotation should take place. Supported cloud
+  // regions: `us-east1`, `us-west1`, `europe-west1`, `asia-east1`. If no region
+  // is specified, a region will be determined based on video file location.
+  string location_id = 5;
+}
+
+// Video context and/or feature-specific parameters.
+message VideoContext {
+  // Video segments to annotate. The segments may overlap and are not required
+  // to be contiguous or span the whole video. If unspecified, each video is
+  // treated as a single segment.
+  repeated VideoSegment segments = 1;
+
+  // Config for LABEL_DETECTION.
+  LabelDetectionConfig label_detection_config = 2;
+
+  // Config for SHOT_CHANGE_DETECTION.
+  ShotChangeDetectionConfig shot_change_detection_config = 3;
+
+  // Config for EXPLICIT_CONTENT_DETECTION.
+  ExplicitContentDetectionConfig explicit_content_detection_config = 4;
+
+  // Config for SPEECH_TRANSCRIPTION.
+  SpeechTranscriptionConfig speech_transcription_config = 6;
+}
+
+// Config for LABEL_DETECTION.
+message LabelDetectionConfig {
+  // What labels should be detected with LABEL_DETECTION, in addition to
+  // video-level labels or segment-level labels.
+  // If unspecified, defaults to `SHOT_MODE`.
+  LabelDetectionMode label_detection_mode = 1;
+
+  // Whether the video has been shot from a stationary (i.e. non-moving) camera.
+  // When set to true, might improve detection accuracy for moving objects.
+  // Should be used with `SHOT_AND_FRAME_MODE` enabled.
+  bool stationary_camera = 2;
+
+  // Model to use for label detection.
+  // Supported values: "builtin/stable" (the default if unset) and
+  // "builtin/latest".
+  string model = 3;
+}
+
+// Config for SHOT_CHANGE_DETECTION.
+message ShotChangeDetectionConfig {
+  // Model to use for shot change detection.
+  // Supported values: "builtin/stable" (the default if unset) and
+  // "builtin/latest".
+  string model = 1;
+}
+
+// Config for EXPLICIT_CONTENT_DETECTION.
+message ExplicitContentDetectionConfig {
+  // Model to use for explicit content detection.
+  // Supported values: "builtin/stable" (the default if unset) and
+  // "builtin/latest".
+  string model = 1;
+}
+
+// Video segment.
+message VideoSegment {
+  // Time-offset, relative to the beginning of the video,
+  // corresponding to the start of the segment (inclusive).
+  google.protobuf.Duration start_time_offset = 1;
+
+  // Time-offset, relative to the beginning of the video,
+  // corresponding to the end of the segment (inclusive).
+  google.protobuf.Duration end_time_offset = 2;
+}
+
+// Video segment level annotation results for label detection.
+message LabelSegment {
+  // Video segment where a label was detected.
+  VideoSegment segment = 1;
+
+  // Confidence that the label is accurate. Range: [0, 1].
+  float confidence = 2;
+}
+
+// Video frame level annotation results for label detection.
+message LabelFrame {
+  // Time-offset, relative to the beginning of the video, corresponding to the
+  // video frame for this location.
+  google.protobuf.Duration time_offset = 1;
+
+  // Confidence that the label is accurate. Range: [0, 1].
+  float confidence = 2;
+}
+
+// Detected entity from video analysis.
+message Entity {
+  // Opaque entity ID. Some IDs may be available in
+  // [Google Knowledge Graph Search
+  // API](https://developers.google.com/knowledge-graph/).
+  string entity_id = 1;
+
+  // Textual description, e.g. `Fixed-gear bicycle`.
+  string description = 2;
+
+  // Language code for `description` in BCP-47 format.
+  string language_code = 3;
+}
+
+// Label annotation.
+message LabelAnnotation {
+  // Detected entity.
+  Entity entity = 1;
+
+  // Common categories for the detected entity.
+  // E.g. when the label is `Terrier` the category is likely `dog`. And in some
+  // cases there might be more than one categories e.g. `Terrier` could also be
+  // a `pet`.
+  repeated Entity category_entities = 2;
+
+  // All video segments where a label was detected.
+  repeated LabelSegment segments = 3;
+
+  // All video frames where a label was detected.
+  repeated LabelFrame frames = 4;
+}
+
+// Video frame level annotation results for explicit content.
+message ExplicitContentFrame {
+  // Time-offset, relative to the beginning of the video, corresponding to the
+  // video frame for this location.
+  google.protobuf.Duration time_offset = 1;
+
+  // Likelihood of the pornography content..
+  Likelihood pornography_likelihood = 2;
+}
+
+// Explicit content annotation (based on per-frame visual signals only).
+// If no explicit content has been detected in a frame, no annotations are
+// present for that frame.
+message ExplicitContentAnnotation {
+  // All video frames where explicit content was detected.
+  repeated ExplicitContentFrame frames = 1;
+}
+
+// Annotation results for a single video.
+message VideoAnnotationResults {
+  // Output only. Video file location in
+  // [Google Cloud Storage](https://cloud.google.com/storage/).
+  string input_uri = 1;
+
+  // Label annotations on video level or user specified segment level.
+  // There is exactly one element for each unique label.
+  repeated LabelAnnotation segment_label_annotations = 2;
+
+  // Label annotations on shot level.
+  // There is exactly one element for each unique label.
+  repeated LabelAnnotation shot_label_annotations = 3;
+
+  // Label annotations on frame level.
+  // There is exactly one element for each unique label.
+  repeated LabelAnnotation frame_label_annotations = 4;
+
+  // Shot annotations. Each shot is represented as a video segment.
+  repeated VideoSegment shot_annotations = 6;
+
+  // Explicit content annotation.
+  ExplicitContentAnnotation explicit_annotation = 7;
+
+  // Speech transcription.
+  repeated SpeechTranscription speech_transcriptions = 11;
+
+  // Output only. If set, indicates an error. Note that for a single
+  // `AnnotateVideoRequest` some videos may succeed and some may fail.
+  google.rpc.Status error = 9;
+}
+
+// Video annotation response. Included in the `response`
+// field of the `Operation` returned by the `GetOperation`
+// call of the `google::longrunning::Operations` service.
+message AnnotateVideoResponse {
+  // Annotation results for all videos specified in `AnnotateVideoRequest`.
+  repeated VideoAnnotationResults annotation_results = 1;
+}
+
+// Annotation progress for a single video.
+message VideoAnnotationProgress {
+  // Output only. Video file location in
+  // [Google Cloud Storage](https://cloud.google.com/storage/).
+  string input_uri = 1;
+
+  // Output only. Approximate percentage processed thus far. Guaranteed to be
+  // 100 when fully processed.
+  int32 progress_percent = 2;
+
+  // Output only. Time when the request was received.
+  google.protobuf.Timestamp start_time = 3;
+
+  // Output only. Time of the most recent update.
+  google.protobuf.Timestamp update_time = 4;
+}
+
+// Video annotation progress. Included in the `metadata`
+// field of the `Operation` returned by the `GetOperation`
+// call of the `google::longrunning::Operations` service.
+message AnnotateVideoProgress {
+  // Progress metadata for all videos specified in `AnnotateVideoRequest`.
+  repeated VideoAnnotationProgress annotation_progress = 1;
+}
+
+// Config for SPEECH_TRANSCRIPTION.
+message SpeechTranscriptionConfig {
+  // *Required* The language of the supplied audio as a
+  // [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
+  // Example: "en-US".
+  // See [Language Support](https://cloud.google.com/speech/docs/languages)
+  // for a list of the currently supported language codes.
+  string language_code = 1;
+
+  // *Optional* Maximum number of recognition hypotheses to be returned.
+  // Specifically, the maximum number of `SpeechRecognitionAlternative` messages
+  // within each `SpeechRecognitionResult`. The server may return fewer than
+  // `max_alternatives`. Valid values are `0`-`30`. A value of `0` or `1` will
+  // return a maximum of one. If omitted, will return a maximum of one.
+  int32 max_alternatives = 2;
+
+  // *Optional* If set to `true`, the server will attempt to filter out
+  // profanities, replacing all but the initial character in each filtered word
+  // with asterisks, e.g. "f***". If set to `false` or omitted, profanities
+  // won't be filtered out.
+  bool filter_profanity = 3;
+
+  // *Optional* A means to provide context to assist the speech recognition.
+  repeated SpeechContext speech_contexts = 4;
+
+  // *Optional* If 'true', adds punctuation to recognition result hypotheses.
+  // This feature is only available in select languages. Setting this for
+  // requests in other languages has no effect at all. The default 'false' value
+  // does not add punctuation to result hypotheses. NOTE: "This is currently
+  // offered as an experimental service, complimentary to all users. In the
+  // future this may be exclusively available as a premium feature."
+  bool enable_automatic_punctuation = 5;
+
+  // *Optional* For file formats, such as MXF or MKV, supporting multiple audio
+  // tracks, specify up to two tracks. Default: track 0.
+  repeated int32 audio_tracks = 6;
+}
+
+// Provides "hints" to the speech recognizer to favor specific words and phrases
+// in the results.
+message SpeechContext {
+  // *Optional* A list of strings containing words and phrases "hints" so that
+  // the speech recognition is more likely to recognize them. This can be used
+  // to improve the accuracy for specific words and phrases, for example, if
+  // specific commands are typically spoken by the user. This can also be used
+  // to add additional words to the vocabulary of the recognizer. See
+  // [usage limits](https://cloud.google.com/speech/limits#content).
+  repeated string phrases = 1;
+}
+
+// A speech recognition result corresponding to a portion of the audio.
+message SpeechTranscription {
+  // Output only. May contain one or more recognition hypotheses (up to the
+  // maximum specified in `max_alternatives`).
+  // These alternatives are ordered in terms of accuracy, with the top (first)
+  // alternative being the most probable, as ranked by the recognizer.
+  repeated SpeechRecognitionAlternative alternatives = 1;
+}
+
+// Alternative hypotheses (a.k.a. n-best list).
+message SpeechRecognitionAlternative {
+  // Output only. Transcript text representing the words that the user spoke.
+  string transcript = 1;
+
+  // Output only. The confidence estimate between 0.0 and 1.0. A higher number
+  // indicates an estimated greater likelihood that the recognized words are
+  // correct. This field is typically provided only for the top hypothesis, and
+  // only for `is_final=true` results. Clients should not rely on the
+  // `confidence` field as it is not guaranteed to be accurate or consistent.
+  // The default of 0.0 is a sentinel value indicating `confidence` was not set.
+  float confidence = 2;
+
+  // Output only. A list of word-specific information for each recognized word.
+  repeated WordInfo words = 3;
+}
+
+// Word-specific information for recognized words. Word information is only
+// included in the response when certain request parameters are set, such
+// as `enable_word_time_offsets`.
+message WordInfo {
+  // Output only. Time offset relative to the beginning of the audio, and
+  // corresponding to the start of the spoken word. This field is only set if
+  // `enable_word_time_offsets=true` and only in the top hypothesis. This is an
+  // experimental feature and the accuracy of the time offset can vary.
+  google.protobuf.Duration start_time = 1;
+
+  // Output only. Time offset relative to the beginning of the audio, and
+  // corresponding to the end of the spoken word. This field is only set if
+  // `enable_word_time_offsets=true` and only in the top hypothesis. This is an
+  // experimental feature and the accuracy of the time offset can vary.
+  google.protobuf.Duration end_time = 2;
+
+  // Output only. The word corresponding to this set of information.
+  string word = 3;
+}
+
+// Video annotation feature.
+enum Feature {
+  // Unspecified.
+  FEATURE_UNSPECIFIED = 0;
+
+  // Label detection. Detect objects, such as dog or flower.
+  LABEL_DETECTION = 1;
+
+  // Shot change detection.
+  SHOT_CHANGE_DETECTION = 2;
+
+  // Explicit content detection.
+  EXPLICIT_CONTENT_DETECTION = 3;
+
+  // Speech transcription.
+  SPEECH_TRANSCRIPTION = 6;
+}
+
+// Label detection mode.
+enum LabelDetectionMode {
+  // Unspecified.
+  LABEL_DETECTION_MODE_UNSPECIFIED = 0;
+
+  // Detect shot-level labels.
+  SHOT_MODE = 1;
+
+  // Detect frame-level labels.
+  FRAME_MODE = 2;
+
+  // Detect both shot-level and frame-level labels.
+  SHOT_AND_FRAME_MODE = 3;
+}
+
+// Bucketized representation of likelihood.
+enum Likelihood {
+  // Unspecified likelihood.
+  LIKELIHOOD_UNSPECIFIED = 0;
+
+  // Very unlikely.
+  VERY_UNLIKELY = 1;
+
+  // Unlikely.
+  UNLIKELY = 2;
+
+  // Possible.
+  POSSIBLE = 3;
+
+  // Likely.
+  LIKELY = 4;
+
+  // Very likely.
+  VERY_LIKELY = 5;
+}