google-cloud-video_intelligence 1.1.2 → 1.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 90fbf75498a2a7aac6b4a6c41b542ff59d10ad2d5fdc2399b8fc1758ba8825de
-  data.tar.gz: 343d0a7a1a83d4173b183f853b76a6c540f43c7d94f0fe83367d74e6e9c97ad9
+  metadata.gz: 17f16aa8f5c1074f53928da96f39f8973c2b5e05a10fd62e3ba4d54c95f1c017
+  data.tar.gz: ca2d14463d0bb2d695667675404f226434d4274f5f330aa1b644f2d2bf37eec9
 SHA512:
-  metadata.gz: 1e4f004ee8225e399442ca19995459bcb6497539c1bbccdf41a87c9dfb22807a12b1cbca58407c089cd664f1cf4c344ee0fb7b44d77fe54a5a3eb1c84722a60b
-  data.tar.gz: 6c1a95f8caea6972839be04f9c46bf71647010c95c1dcb1fa337ed83d748b606c53bd946bd49bfc6cfc8ed0abe22dc97c13508a1458abad213b035a871bc0fd2
+  metadata.gz: 4f50bdb3012b53f9eeb036e25985dfc82d783131a687671c7dabb6260a190306a9716d0618215b65a8b7db92df369c155d9cd59bb7f78457ed8f19e8a1ef2f0f
+  data.tar.gz: 9f4375e444a101a90f8aecfe65dfb54d587f3fc1c84bb617ef7bf58688b3f3142882eeb3dd9f5f7ca4d822a8c67dff4deedbdb5465ef7d259aa07833b0997262

data/lib/google/cloud/video_intelligence/v1/doc/google/cloud/videointelligence/v1/video_intelligence.rb

@@ -60,8 +60,8 @@ module Google
         # @!attribute [rw] segments
         #   @return [Array<Google::Cloud::Videointelligence::V1::VideoSegment>]
         #     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.
+        #     to be contiguous or span the whole video. If unspecified, each video is
+        #     treated as a single segment.
         # @!attribute [rw] label_detection_config
         #   @return [Google::Cloud::Videointelligence::V1::LabelDetectionConfig]
         #     Config for LABEL_DETECTION.
@@ -74,6 +74,9 @@ module Google
         # @!attribute [rw] face_detection_config
         #   @return [Google::Cloud::Videointelligence::V1::FaceDetectionConfig]
         #     Config for FACE_DETECTION.
+        # @!attribute [rw] speech_transcription_config
+        #   @return [Google::Cloud::Videointelligence::V1::SpeechTranscriptionConfig]
+        #     Config for SPEECH_TRANSCRIPTION.
         class VideoContext; end
 
         # Config for LABEL_DETECTION.
@@ -274,6 +277,9 @@ module Google
         # @!attribute [rw] explicit_annotation
         #   @return [Google::Cloud::Videointelligence::V1::ExplicitContentAnnotation]
         #     Explicit content annotation.
+        # @!attribute [rw] speech_transcriptions
+        #   @return [Array<Google::Cloud::Videointelligence::V1::SpeechTranscription>]
+        #     Speech transcription.
         # @!attribute [rw] error
         #   @return [Google::Rpc::Status]
         #     If set, indicates an error. Note that for a single `AnnotateVideoRequest`
@@ -295,8 +301,8 @@ module Google
         #     [Google Cloud Storage](https://cloud.google.com/storage/).
         # @!attribute [rw] progress_percent
         #   @return [Integer]
-        #     Approximate percentage processed thus far.
-        #     Guaranteed to be 100 when fully processed.
+        #     Approximate percentage processed thus far. Guaranteed to be
+        #     100 when fully processed.
         # @!attribute [rw] start_time
         #   @return [Google::Protobuf::Timestamp]
         #     Time when the request was received.
@@ -313,6 +319,142 @@ module Google
         #     Progress metadata for all videos specified in `AnnotateVideoRequest`.
         class AnnotateVideoProgress; end
 
+        # Config for SPEECH_TRANSCRIPTION.
+        # @!attribute [rw] language_code
+        #   @return [String]
+        #     *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.
+        # @!attribute [rw] max_alternatives
+        #   @return [Integer]
+        #     *Optional* Maximum number of recognition hypotheses to be returned.
+        #     Specifically, the maximum number of `SpeechRecognitionAlternative` messages
+        #     within each `SpeechTranscription`. The server may return fewer than
+        #     `max_alternatives`. Valid values are `0`-`30`. A value of `0` or `1` will
+        #     return a maximum of one. If omitted, will return a maximum of one.
+        # @!attribute [rw] filter_profanity
+        #   @return [true, false]
+        #     *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.
+        # @!attribute [rw] speech_contexts
+        #   @return [Array<Google::Cloud::Videointelligence::V1::SpeechContext>]
+        #     *Optional* A means to provide context to assist the speech recognition.
+        # @!attribute [rw] enable_automatic_punctuation
+        #   @return [true, false]
+        #     *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."
+        # @!attribute [rw] audio_tracks
+        #   @return [Array<Integer>]
+        #     *Optional* For file formats, such as MXF or MKV, supporting multiple audio
+        #     tracks, specify up to two tracks. Default: track 0.
+        # @!attribute [rw] enable_speaker_diarization
+        #   @return [true, false]
+        #     *Optional* If 'true', enables speaker detection for each recognized word in
+        #     the top alternative of the recognition result using a speaker_tag provided
+        #     in the WordInfo.
+        #     Note: When this is true, we send all the words from the beginning of the
+        #     audio for the top alternative in every consecutive responses.
+        #     This is done in order to improve our speaker tags as our models learn to
+        #     identify the speakers in the conversation over time.
+        # @!attribute [rw] diarization_speaker_count
+        #   @return [Integer]
+        #     *Optional*
+        #     If set, specifies the estimated number of speakers in the conversation.
+        #     If not set, defaults to '2'.
+        #     Ignored unless enable_speaker_diarization is set to true.
+        # @!attribute [rw] enable_word_confidence
+        #   @return [true, false]
+        #     *Optional* If `true`, the top result includes a list of words and the
+        #     confidence for those words. If `false`, no word-level confidence
+        #     information is returned. The default is `false`.
+        class SpeechTranscriptionConfig; end
+
+        # Provides "hints" to the speech recognizer to favor specific words and phrases
+        # in the results.
+        # @!attribute [rw] phrases
+        #   @return [Array<String>]
+        #     *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).
+        class SpeechContext; end
+
+        # A speech recognition result corresponding to a portion of the audio.
+        # @!attribute [rw] alternatives
+        #   @return [Array<Google::Cloud::Videointelligence::V1::SpeechRecognitionAlternative>]
+        #     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.
+        # @!attribute [rw] language_code
+        #   @return [String]
+        #     Output only. The
+        #     [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the
+        #     language in this result. This language code was detected to have the most
+        #     likelihood of being spoken in the audio.
+        class SpeechTranscription; end
+
+        # Alternative hypotheses (a.k.a. n-best list).
+        # @!attribute [rw] transcript
+        #   @return [String]
+        #     Transcript text representing the words that the user spoke.
+        # @!attribute [rw] confidence
+        #   @return [Float]
+        #     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.
+        # @!attribute [rw] words
+        #   @return [Array<Google::Cloud::Videointelligence::V1::WordInfo>]
+        #     A list of word-specific information for each recognized word.
+        class SpeechRecognitionAlternative; end
+
+        # 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`.
+        # @!attribute [rw] start_time
+        #   @return [Google::Protobuf::Duration]
+        #     Time offset relative to the beginning of the audio, and
+        #     corresponding to the start of the spoken word. This field is only set if
+        #     `enable_word_time_offsets=true` and only in the top hypothesis. This is an
+        #     experimental feature and the accuracy of the time offset can vary.
+        # @!attribute [rw] end_time
+        #   @return [Google::Protobuf::Duration]
+        #     Time offset relative to the beginning of the audio, and
+        #     corresponding to the end of the spoken word. This field is only set if
+        #     `enable_word_time_offsets=true` and only in the top hypothesis. This is an
+        #     experimental feature and the accuracy of the time offset can vary.
+        # @!attribute [rw] word
+        #   @return [String]
+        #     The word corresponding to this set of information.
+        # @!attribute [rw] confidence
+        #   @return [Float]
+        #     Output only. The confidence estimate between 0.0 and 1.0. A higher number
+        #     indicates an estimated greater likelihood that the recognized words are
+        #     correct. This field is set only for the top alternative.
+        #     This field is not guaranteed to be accurate and users should not rely on it
+        #     to be always provided.
+        #     The default of 0.0 is a sentinel value indicating `confidence` was not set.
+        # @!attribute [rw] speaker_tag
+        #   @return [Integer]
+        #     Output only. A distinct integer value is assigned for every speaker within
+        #     the audio. This field specifies which one of those speakers was detected to
+        #     have spoken this word. Value ranges from 1 up to diarization_speaker_count,
+        #     and is only set if speaker diarization is enabled.
+        class WordInfo; end
+
         # Video annotation feature.
         module Feature
           # Unspecified.
@@ -329,6 +471,9 @@ module Google
 
           # Human face detection and tracking.
           FACE_DETECTION = 4
+
+          # Speech transcription.
+          SPEECH_TRANSCRIPTION = 6
         end
 
         # Label detection mode.

data/lib/google/cloud/video_intelligence/v1/video_intelligence_service_client_config.json

@@ -21,7 +21,7 @@
       },
       "methods": {
         "AnnotateVideo": {
-          "timeout_millis": 60000,
+          "timeout_millis": 600000,
           "retry_codes_name": "idempotent",
           "retry_params_name": "default"
         }

data/lib/google/cloud/video_intelligence/v1p1beta1.rb

@@ -0,0 +1,177 @@
+# Copyright 2018 Google LLC
+#
+# 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
+#
+#     https://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.
+
+
+require "google/cloud/video_intelligence/v1p1beta1/video_intelligence_service_client"
+require "google/rpc/status_pb"
+require "google/cloud/videointelligence/v1p1beta1/video_intelligence_pb"
+
+module Google
+  module Cloud
+    module VideoIntelligence
+      # rubocop:disable LineLength
+
+      ##
+      # # Ruby Client for Cloud Video Intelligence API ([Beta](https://github.com/googleapis/google-cloud-ruby#versioning))
+      #
+      # [Cloud Video Intelligence API][Product Documentation]:
+      # Cloud Video Intelligence API.
+      # - [Product Documentation][]
+      #
+      # ## Quick Start
+      # In order to use this library, you first need to go through the following
+      # steps:
+      #
+      # 1. [Select or create a Cloud Platform project.](https://console.cloud.google.com/project)
+      # 2. [Enable billing for your project.](https://cloud.google.com/billing/docs/how-to/modify-project#enable_billing_for_a_project)
+      # 3. [Enable the Cloud Video Intelligence API.](https://console.cloud.google.com/apis/library/videointelligence.googleapis.com)
+      # 4. [Setup Authentication.](https://googleapis.github.io/google-cloud-ruby/#/docs/google-cloud/master/guides/authentication)
+      #
+      # ### Installation
+      # ```
+      # $ gem install google-cloud-video_intelligence
+      # ```
+      #
+      # ### Preview
+      # #### VideoIntelligenceServiceClient
+      # ```rb
+      # require "google/cloud/video_intelligence"
+      #
+      # video_intelligence_service_client = Google::Cloud::VideoIntelligence.new(version: :v1p1beta1)
+      # input_uri = "gs://demomaker/cat.mp4"
+      # features_element = :LABEL_DETECTION
+      # features = [features_element]
+      #
+      # # Register a callback during the method call.
+      # operation = video_intelligence_service_client.annotate_video(input_uri: input_uri, features: features) do |op|
+      #   raise op.results.message if op.error?
+      #   op_results = op.results
+      #   # Process the results.
+      #
+      #   metadata = op.metadata
+      #   # Process the metadata.
+      # end
+      #
+      # # Or use the return value to register a callback.
+      # operation.on_done do |op|
+      #   raise op.results.message if op.error?
+      #   op_results = op.results
+      #   # Process the results.
+      #
+      #   metadata = op.metadata
+      #   # Process the metadata.
+      # end
+      #
+      # # Manually reload the operation.
+      # operation.reload!
+      #
+      # # Or block until the operation completes, triggering callbacks on
+      # # completion.
+      # operation.wait_until_done!
+      # ```
+      #
+      # ### Next Steps
+      # - Read the [Cloud Video Intelligence API Product documentation][Product Documentation]
+      #   to learn more about the product and see How-to Guides.
+      # - View this [repository's main README](https://github.com/googleapis/google-cloud-ruby/blob/master/README.md)
+      #   to see the full list of Cloud APIs that we cover.
+      #
+      # [Product Documentation]: https://cloud.google.com/video-intelligence
+      #
+      # ## Enabling Logging
+      #
+      # To enable logging for this library, set the logger for the underlying [gRPC](https://github.com/grpc/grpc/tree/master/src/ruby) library.
+      # The logger that you set may be a Ruby stdlib [`Logger`](https://ruby-doc.org/stdlib-2.5.0/libdoc/logger/rdoc/Logger.html) as shown below,
+      # or a [`Google::Cloud::Logging::Logger`](https://googleapis.github.io/google-cloud-ruby/#/docs/google-cloud-logging/latest/google/cloud/logging/logger)
+      # that will write logs to [Stackdriver Logging](https://cloud.google.com/logging/). See [grpc/logconfig.rb](https://github.com/grpc/grpc/blob/master/src/ruby/lib/grpc/logconfig.rb)
+      # and the gRPC [spec_helper.rb](https://github.com/grpc/grpc/blob/master/src/ruby/spec/spec_helper.rb) for additional information.
+      #
+      # Configuring a Ruby stdlib logger:
+      #
+      # ```ruby
+      # require "logger"
+      #
+      # module MyLogger
+      #   LOGGER = Logger.new $stderr, level: Logger::WARN
+      #   def logger
+      #     LOGGER
+      #   end
+      # end
+      #
+      # # Define a gRPC module-level logger method before grpc/logconfig.rb loads.
+      # module GRPC
+      #   extend MyLogger
+      # end
+      # ```
+      #
+      module V1p1beta1
+        # rubocop:enable LineLength
+
+        ##
+        # Service that implements Google Cloud Video Intelligence API.
+        #
+        # @param credentials [Google::Auth::Credentials, String, Hash, GRPC::Core::Channel, GRPC::Core::ChannelCredentials, Proc]
+        #   Provides the means for authenticating requests made by the client. This parameter can
+        #   be many types.
+        #   A `Google::Auth::Credentials` uses a the properties of its represented keyfile for
+        #   authenticating requests made by this client.
+        #   A `String` will be treated as the path to the keyfile to be used for the construction of
+        #   credentials for this client.
+        #   A `Hash` will be treated as the contents of a keyfile to be used for the construction of
+        #   credentials for this client.
+        #   A `GRPC::Core::Channel` will be used to make calls through.
+        #   A `GRPC::Core::ChannelCredentials` for the setting up the RPC client. The channel credentials
+        #   should already be composed with a `GRPC::Core::CallCredentials` object.
+        #   A `Proc` will be used as an updater_proc for the Grpc channel. The proc transforms the
+        #   metadata for requests, generally, to give OAuth credentials.
+        # @param scopes [Array<String>]
+        #   The OAuth scopes for this service. This parameter is ignored if
+        #   an updater_proc is supplied.
+        # @param client_config [Hash]
+        #   A Hash for call options for each method. See
+        #   Google::Gax#construct_settings for the structure of
+        #   this data. Falls back to the default config if not specified
+        #   or the specified config is missing data points.
+        # @param timeout [Numeric]
+        #   The default timeout, in seconds, for calls made through this client.
+        # @param metadata [Hash]
+        #   Default metadata to be sent with each request. This can be overridden on a per call basis.
+        # @param exception_transformer [Proc]
+        #   An optional proc that intercepts any exceptions raised during an API call to inject
+        #   custom error handling.
+        def self.new \
+            credentials: nil,
+            scopes: nil,
+            client_config: nil,
+            timeout: nil,
+            metadata: nil,
+            exception_transformer: nil,
+            lib_name: nil,
+            lib_version: nil
+          kwargs = {
+            credentials: credentials,
+            scopes: scopes,
+            client_config: client_config,
+            timeout: timeout,
+            metadata: metadata,
+            exception_transformer: exception_transformer,
+            lib_name: lib_name,
+            lib_version: lib_version
+          }.select { |_, v| v != nil }
+          Google::Cloud::VideoIntelligence::V1p1beta1::VideoIntelligenceServiceClient.new(**kwargs)
+        end
+      end
+    end
+  end
+end

data/lib/google/cloud/video_intelligence/v1p1beta1/credentials.rb

@@ -0,0 +1,41 @@
+# Copyright 2018 Google LLC
+#
+# 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
+#
+#     https://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.
+
+
+require "googleauth"
+
+module Google
+  module Cloud
+    module VideoIntelligence
+      module V1p1beta1
+        class Credentials < Google::Auth::Credentials
+          SCOPE = [
+            "https://www.googleapis.com/auth/cloud-platform"
+          ].freeze
+          PATH_ENV_VARS = %w(VIDEO_INTELLIGENCE_CREDENTIALS
+                             VIDEO_INTELLIGENCE_KEYFILE
+                             GOOGLE_CLOUD_CREDENTIALS
+                             GOOGLE_CLOUD_KEYFILE
+                             GCLOUD_KEYFILE)
+          JSON_ENV_VARS = %w(VIDEO_INTELLIGENCE_CREDENTIALS_JSON
+                             VIDEO_INTELLIGENCE_KEYFILE_JSON
+                             GOOGLE_CLOUD_CREDENTIALS_JSON
+                             GOOGLE_CLOUD_KEYFILE_JSON
+                             GCLOUD_KEYFILE_JSON)
+          DEFAULT_PATHS = ["~/.config/gcloud/application_default_credentials.json"]
+        end
+      end
+    end
+  end
+end

data/lib/google/cloud/video_intelligence/v1p1beta1/doc/google/cloud/videointelligence/v1p1beta1/video_intelligence.rb

@@ -0,0 +1,410 @@
+# Copyright 2018 Google LLC
+#
+# 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
+#
+#     https://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.
+
+
+module Google
+  module Cloud
+    module Videointelligence
+      module V1p1beta1
+        # Video annotation request.
+        # @!attribute [rw] input_uri
+        #   @return [String]
+        #     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}). For more information, see
+        #     [Request URIs](https://cloud.google.com/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.
+        # @!attribute [rw] input_content
+        #   @return [String]
+        #     The video data bytes.
+        #     If unset, the input video(s) should be specified via `input_uri`.
+        #     If set, `input_uri` should be unset.
+        # @!attribute [rw] features
+        #   @return [Array<Google::Cloud::Videointelligence::V1p1beta1::Feature>]
+        #     Requested video annotation features.
+        # @!attribute [rw] video_context
+        #   @return [Google::Cloud::Videointelligence::V1p1beta1::VideoContext]
+        #     Additional video context and/or feature-specific parameters.
+        # @!attribute [rw] output_uri
+        #   @return [String]
+        #     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}). For more information, see
+        #     [Request URIs](https://cloud.google.com/storage/docs/reference-uris).
+        # @!attribute [rw] location_id
+        #   @return [String]
+        #     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.
+        class AnnotateVideoRequest; end
+
+        # Video context and/or feature-specific parameters.
+        # @!attribute [rw] segments
+        #   @return [Array<Google::Cloud::Videointelligence::V1p1beta1::VideoSegment>]
+        #     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.
+        # @!attribute [rw] label_detection_config
+        #   @return [Google::Cloud::Videointelligence::V1p1beta1::LabelDetectionConfig]
+        #     Config for LABEL_DETECTION.
+        # @!attribute [rw] shot_change_detection_config
+        #   @return [Google::Cloud::Videointelligence::V1p1beta1::ShotChangeDetectionConfig]
+        #     Config for SHOT_CHANGE_DETECTION.
+        # @!attribute [rw] explicit_content_detection_config
+        #   @return [Google::Cloud::Videointelligence::V1p1beta1::ExplicitContentDetectionConfig]
+        #     Config for EXPLICIT_CONTENT_DETECTION.
+        # @!attribute [rw] speech_transcription_config
+        #   @return [Google::Cloud::Videointelligence::V1p1beta1::SpeechTranscriptionConfig]
+        #     Config for SPEECH_TRANSCRIPTION.
+        class VideoContext; end
+
+        # Config for LABEL_DETECTION.
+        # @!attribute [rw] label_detection_mode
+        #   @return [Google::Cloud::Videointelligence::V1p1beta1::LabelDetectionMode]
+        #     What labels should be detected with LABEL_DETECTION, in addition to
+        #     video-level labels or segment-level labels.
+        #     If unspecified, defaults to `SHOT_MODE`.
+        # @!attribute [rw] stationary_camera
+        #   @return [true, false]
+        #     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.
+        # @!attribute [rw] model
+        #   @return [String]
+        #     Model to use for label detection.
+        #     Supported values: "builtin/stable" (the default if unset) and
+        #     "builtin/latest".
+        class LabelDetectionConfig; end
+
+        # Config for SHOT_CHANGE_DETECTION.
+        # @!attribute [rw] model
+        #   @return [String]
+        #     Model to use for shot change detection.
+        #     Supported values: "builtin/stable" (the default if unset) and
+        #     "builtin/latest".
+        class ShotChangeDetectionConfig; end
+
+        # Config for EXPLICIT_CONTENT_DETECTION.
+        # @!attribute [rw] model
+        #   @return [String]
+        #     Model to use for explicit content detection.
+        #     Supported values: "builtin/stable" (the default if unset) and
+        #     "builtin/latest".
+        class ExplicitContentDetectionConfig; end
+
+        # Video segment.
+        # @!attribute [rw] start_time_offset
+        #   @return [Google::Protobuf::Duration]
+        #     Time-offset, relative to the beginning of the video,
+        #     corresponding to the start of the segment (inclusive).
+        # @!attribute [rw] end_time_offset
+        #   @return [Google::Protobuf::Duration]
+        #     Time-offset, relative to the beginning of the video,
+        #     corresponding to the end of the segment (inclusive).
+        class VideoSegment; end
+
+        # Video segment level annotation results for label detection.
+        # @!attribute [rw] segment
+        #   @return [Google::Cloud::Videointelligence::V1p1beta1::VideoSegment]
+        #     Video segment where a label was detected.
+        # @!attribute [rw] confidence
+        #   @return [Float]
+        #     Confidence that the label is accurate. Range: [0, 1].
+        class LabelSegment; end
+
+        # Video frame level annotation results for label detection.
+        # @!attribute [rw] time_offset
+        #   @return [Google::Protobuf::Duration]
+        #     Time-offset, relative to the beginning of the video, corresponding to the
+        #     video frame for this location.
+        # @!attribute [rw] confidence
+        #   @return [Float]
+        #     Confidence that the label is accurate. Range: [0, 1].
+        class LabelFrame; end
+
+        # Detected entity from video analysis.
+        # @!attribute [rw] entity_id
+        #   @return [String]
+        #     Opaque entity ID. Some IDs may be available in
+        #     [Google Knowledge Graph Search
+        #     API](https://developers.google.com/knowledge-graph/).
+        # @!attribute [rw] description
+        #   @return [String]
+        #     Textual description, e.g. `Fixed-gear bicycle`.
+        # @!attribute [rw] language_code
+        #   @return [String]
+        #     Language code for `description` in BCP-47 format.
+        class Entity; end
+
+        # Label annotation.
+        # @!attribute [rw] entity
+        #   @return [Google::Cloud::Videointelligence::V1p1beta1::Entity]
+        #     Detected entity.
+        # @!attribute [rw] category_entities
+        #   @return [Array<Google::Cloud::Videointelligence::V1p1beta1::Entity>]
+        #     Common categories for the detected entity.
+        #     E.g. when the label is `Terrier` the category is likely `dog`. And in some
+        #     cases there might be more than one categories e.g. `Terrier` could also be
+        #     a `pet`.
+        # @!attribute [rw] segments
+        #   @return [Array<Google::Cloud::Videointelligence::V1p1beta1::LabelSegment>]
+        #     All video segments where a label was detected.
+        # @!attribute [rw] frames
+        #   @return [Array<Google::Cloud::Videointelligence::V1p1beta1::LabelFrame>]
+        #     All video frames where a label was detected.
+        class LabelAnnotation; end
+
+        # Video frame level annotation results for explicit content.
+        # @!attribute [rw] time_offset
+        #   @return [Google::Protobuf::Duration]
+        #     Time-offset, relative to the beginning of the video, corresponding to the
+        #     video frame for this location.
+        # @!attribute [rw] pornography_likelihood
+        #   @return [Google::Cloud::Videointelligence::V1p1beta1::Likelihood]
+        #     Likelihood of the pornography content..
+        class ExplicitContentFrame; end
+
+        # 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.
+        # @!attribute [rw] frames
+        #   @return [Array<Google::Cloud::Videointelligence::V1p1beta1::ExplicitContentFrame>]
+        #     All video frames where explicit content was detected.
+        class ExplicitContentAnnotation; end
+
+        # Annotation results for a single video.
+        # @!attribute [rw] input_uri
+        #   @return [String]
+        #     Output only. Video file location in
+        #     [Google Cloud Storage](https://cloud.google.com/storage/).
+        # @!attribute [rw] segment_label_annotations
+        #   @return [Array<Google::Cloud::Videointelligence::V1p1beta1::LabelAnnotation>]
+        #     Label annotations on video level or user specified segment level.
+        #     There is exactly one element for each unique label.
+        # @!attribute [rw] shot_label_annotations
+        #   @return [Array<Google::Cloud::Videointelligence::V1p1beta1::LabelAnnotation>]
+        #     Label annotations on shot level.
+        #     There is exactly one element for each unique label.
+        # @!attribute [rw] frame_label_annotations
+        #   @return [Array<Google::Cloud::Videointelligence::V1p1beta1::LabelAnnotation>]
+        #     Label annotations on frame level.
+        #     There is exactly one element for each unique label.
+        # @!attribute [rw] shot_annotations
+        #   @return [Array<Google::Cloud::Videointelligence::V1p1beta1::VideoSegment>]
+        #     Shot annotations. Each shot is represented as a video segment.
+        # @!attribute [rw] explicit_annotation
+        #   @return [Google::Cloud::Videointelligence::V1p1beta1::ExplicitContentAnnotation]
+        #     Explicit content annotation.
+        # @!attribute [rw] speech_transcriptions
+        #   @return [Array<Google::Cloud::Videointelligence::V1p1beta1::SpeechTranscription>]
+        #     Speech transcription.
+        # @!attribute [rw] error
+        #   @return [Google::Rpc::Status]
+        #     Output only. If set, indicates an error. Note that for a single
+        #     `AnnotateVideoRequest` some videos may succeed and some may fail.
+        class VideoAnnotationResults; end
+
+        # Video annotation response. Included in the `response`
+        # field of the `Operation` returned by the `GetOperation`
+        # call of the `google::longrunning::Operations` service.
+        # @!attribute [rw] annotation_results
+        #   @return [Array<Google::Cloud::Videointelligence::V1p1beta1::VideoAnnotationResults>]
+        #     Annotation results for all videos specified in `AnnotateVideoRequest`.
+        class AnnotateVideoResponse; end
+
+        # Annotation progress for a single video.
+        # @!attribute [rw] input_uri
+        #   @return [String]
+        #     Output only. Video file location in
+        #     [Google Cloud Storage](https://cloud.google.com/storage/).
+        # @!attribute [rw] progress_percent
+        #   @return [Integer]
+        #     Output only. Approximate percentage processed thus far. Guaranteed to be
+        #     100 when fully processed.
+        # @!attribute [rw] start_time
+        #   @return [Google::Protobuf::Timestamp]
+        #     Output only. Time when the request was received.
+        # @!attribute [rw] update_time
+        #   @return [Google::Protobuf::Timestamp]
+        #     Output only. Time of the most recent update.
+        class VideoAnnotationProgress; end
+
+        # Video annotation progress. Included in the `metadata`
+        # field of the `Operation` returned by the `GetOperation`
+        # call of the `google::longrunning::Operations` service.
+        # @!attribute [rw] annotation_progress
+        #   @return [Array<Google::Cloud::Videointelligence::V1p1beta1::VideoAnnotationProgress>]
+        #     Progress metadata for all videos specified in `AnnotateVideoRequest`.
+        class AnnotateVideoProgress; end
+
+        # Config for SPEECH_TRANSCRIPTION.
+        # @!attribute [rw] language_code
+        #   @return [String]
+        #     *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.
+        # @!attribute [rw] max_alternatives
+        #   @return [Integer]
+        #     *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.
+        # @!attribute [rw] filter_profanity
+        #   @return [true, false]
+        #     *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.
+        # @!attribute [rw] speech_contexts
+        #   @return [Array<Google::Cloud::Videointelligence::V1p1beta1::SpeechContext>]
+        #     *Optional* A means to provide context to assist the speech recognition.
+        # @!attribute [rw] enable_automatic_punctuation
+        #   @return [true, false]
+        #     *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."
+        # @!attribute [rw] audio_tracks
+        #   @return [Array<Integer>]
+        #     *Optional* For file formats, such as MXF or MKV, supporting multiple audio
+        #     tracks, specify up to two tracks. Default: track 0.
+        class SpeechTranscriptionConfig; end
+
+        # Provides "hints" to the speech recognizer to favor specific words and phrases
+        # in the results.
+        # @!attribute [rw] phrases
+        #   @return [Array<String>]
+        #     *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).
+        class SpeechContext; end
+
+        # A speech recognition result corresponding to a portion of the audio.
+        # @!attribute [rw] alternatives
+        #   @return [Array<Google::Cloud::Videointelligence::V1p1beta1::SpeechRecognitionAlternative>]
+        #     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.
+        class SpeechTranscription; end
+
+        # Alternative hypotheses (a.k.a. n-best list).
+        # @!attribute [rw] transcript
+        #   @return [String]
+        #     Output only. Transcript text representing the words that the user spoke.
+        # @!attribute [rw] confidence
+        #   @return [Float]
+        #     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.
+        # @!attribute [rw] words
+        #   @return [Array<Google::Cloud::Videointelligence::V1p1beta1::WordInfo>]
+        #     Output only. A list of word-specific information for each recognized word.
+        class SpeechRecognitionAlternative; end
+
+        # 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`.
+        # @!attribute [rw] start_time
+        #   @return [Google::Protobuf::Duration]
+        #     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.
+        # @!attribute [rw] end_time
+        #   @return [Google::Protobuf::Duration]
+        #     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.
+        # @!attribute [rw] word
+        #   @return [String]
+        #     Output only. The word corresponding to this set of information.
+        class WordInfo; end
+
+        # Video annotation feature.
+        module 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
+        end
+
+        # Label detection mode.
+        module 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
+        end
+
+        # Bucketized representation of likelihood.
+        module 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
+        end
+      end
+    end
+  end
+end