google-api-client 0.24.3 → 0.25.0

data/generated/google/apis/videointelligence_v1beta2/representations.rb

@@ -70,6 +70,18 @@ module Google
         include Google::Apis::Core::JsonObjectSupport
       end
       
+      class GoogleCloudVideointelligenceV1SpeechRecognitionAlternative
+        class Representation < Google::Apis::Core::JsonRepresentation; end
+      
+        include Google::Apis::Core::JsonObjectSupport
+      end
+      
+      class GoogleCloudVideointelligenceV1SpeechTranscription
+        class Representation < Google::Apis::Core::JsonRepresentation; end
+      
+        include Google::Apis::Core::JsonObjectSupport
+      end
+      
       class GoogleCloudVideointelligenceV1VideoAnnotationProgress
         class Representation < Google::Apis::Core::JsonRepresentation; end
       
@@ -88,6 +100,12 @@ module Google
         include Google::Apis::Core::JsonObjectSupport
       end
       
+      class GoogleCloudVideointelligenceV1WordInfo
+        class Representation < Google::Apis::Core::JsonRepresentation; end
+      
+        include Google::Apis::Core::JsonObjectSupport
+      end
+      
       class GoogleCloudVideointelligenceV1beta2AnnotateVideoProgress
         class Representation < Google::Apis::Core::JsonRepresentation; end
       
@@ -160,6 +178,30 @@ module Google
         include Google::Apis::Core::JsonObjectSupport
       end
       
+      class GoogleCloudVideointelligenceV1beta2SpeechContext
+        class Representation < Google::Apis::Core::JsonRepresentation; end
+      
+        include Google::Apis::Core::JsonObjectSupport
+      end
+      
+      class GoogleCloudVideointelligenceV1beta2SpeechRecognitionAlternative
+        class Representation < Google::Apis::Core::JsonRepresentation; end
+      
+        include Google::Apis::Core::JsonObjectSupport
+      end
+      
+      class GoogleCloudVideointelligenceV1beta2SpeechTranscription
+        class Representation < Google::Apis::Core::JsonRepresentation; end
+      
+        include Google::Apis::Core::JsonObjectSupport
+      end
+      
+      class GoogleCloudVideointelligenceV1beta2SpeechTranscriptionConfig
+        class Representation < Google::Apis::Core::JsonRepresentation; end
+      
+        include Google::Apis::Core::JsonObjectSupport
+      end
+      
       class GoogleCloudVideointelligenceV1beta2VideoAnnotationProgress
         class Representation < Google::Apis::Core::JsonRepresentation; end
       
@@ -184,6 +226,12 @@ module Google
         include Google::Apis::Core::JsonObjectSupport
       end
       
+      class GoogleCloudVideointelligenceV1beta2WordInfo
+        class Representation < Google::Apis::Core::JsonRepresentation; end
+      
+        include Google::Apis::Core::JsonObjectSupport
+      end
+      
       class GoogleCloudVideointelligenceV1p1beta1AnnotateVideoProgress
         class Representation < Google::Apis::Core::JsonRepresentation; end
       
@@ -346,6 +394,18 @@ module Google
         include Google::Apis::Core::JsonObjectSupport
       end
       
+      class GoogleCloudVideointelligenceV1p2beta1SpeechRecognitionAlternative
+        class Representation < Google::Apis::Core::JsonRepresentation; end
+      
+        include Google::Apis::Core::JsonObjectSupport
+      end
+      
+      class GoogleCloudVideointelligenceV1p2beta1SpeechTranscription
+        class Representation < Google::Apis::Core::JsonRepresentation; end
+      
+        include Google::Apis::Core::JsonObjectSupport
+      end
+      
       class GoogleCloudVideointelligenceV1p2beta1TextAnnotation
         class Representation < Google::Apis::Core::JsonRepresentation; end
       
@@ -382,6 +442,12 @@ module Google
         include Google::Apis::Core::JsonObjectSupport
       end
       
+      class GoogleCloudVideointelligenceV1p2beta1WordInfo
+        class Representation < Google::Apis::Core::JsonRepresentation; end
+      
+        include Google::Apis::Core::JsonObjectSupport
+      end
+      
       class GoogleLongrunningOperation
         class Representation < Google::Apis::Core::JsonRepresentation; end
       
@@ -466,6 +532,25 @@ module Google
         end
       end
       
+      class GoogleCloudVideointelligenceV1SpeechRecognitionAlternative
+        # @private
+        class Representation < Google::Apis::Core::JsonRepresentation
+          property :confidence, as: 'confidence'
+          property :transcript, as: 'transcript'
+          collection :words, as: 'words', class: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1WordInfo, decorator: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1WordInfo::Representation
+      
+        end
+      end
+      
+      class GoogleCloudVideointelligenceV1SpeechTranscription
+        # @private
+        class Representation < Google::Apis::Core::JsonRepresentation
+          collection :alternatives, as: 'alternatives', class: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1SpeechRecognitionAlternative, decorator: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1SpeechRecognitionAlternative::Representation
+      
+          property :language_code, as: 'languageCode'
+        end
+      end
+      
       class GoogleCloudVideointelligenceV1VideoAnnotationProgress
         # @private
         class Representation < Google::Apis::Core::JsonRepresentation
@@ -492,6 +577,8 @@ module Google
       
           collection :shot_label_annotations, as: 'shotLabelAnnotations', class: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1LabelAnnotation, decorator: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1LabelAnnotation::Representation
       
+          collection :speech_transcriptions, as: 'speechTranscriptions', class: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1SpeechTranscription, decorator: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1SpeechTranscription::Representation
+      
         end
       end
       
@@ -503,6 +590,17 @@ module Google
         end
       end
       
+      class GoogleCloudVideointelligenceV1WordInfo
+        # @private
+        class Representation < Google::Apis::Core::JsonRepresentation
+          property :confidence, as: 'confidence'
+          property :end_time, as: 'endTime'
+          property :speaker_tag, as: 'speakerTag'
+          property :start_time, as: 'startTime'
+          property :word, as: 'word'
+        end
+      end
+      
       class GoogleCloudVideointelligenceV1beta2AnnotateVideoProgress
         # @private
         class Representation < Google::Apis::Core::JsonRepresentation
@@ -611,6 +709,48 @@ module Google
         end
       end
       
+      class GoogleCloudVideointelligenceV1beta2SpeechContext
+        # @private
+        class Representation < Google::Apis::Core::JsonRepresentation
+          collection :phrases, as: 'phrases'
+        end
+      end
+      
+      class GoogleCloudVideointelligenceV1beta2SpeechRecognitionAlternative
+        # @private
+        class Representation < Google::Apis::Core::JsonRepresentation
+          property :confidence, as: 'confidence'
+          property :transcript, as: 'transcript'
+          collection :words, as: 'words', class: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1beta2WordInfo, decorator: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1beta2WordInfo::Representation
+      
+        end
+      end
+      
+      class GoogleCloudVideointelligenceV1beta2SpeechTranscription
+        # @private
+        class Representation < Google::Apis::Core::JsonRepresentation
+          collection :alternatives, as: 'alternatives', class: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1beta2SpeechRecognitionAlternative, decorator: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1beta2SpeechRecognitionAlternative::Representation
+      
+          property :language_code, as: 'languageCode'
+        end
+      end
+      
+      class GoogleCloudVideointelligenceV1beta2SpeechTranscriptionConfig
+        # @private
+        class Representation < Google::Apis::Core::JsonRepresentation
+          collection :audio_tracks, as: 'audioTracks'
+          property :diarization_speaker_count, as: 'diarizationSpeakerCount'
+          property :enable_automatic_punctuation, as: 'enableAutomaticPunctuation'
+          property :enable_speaker_diarization, as: 'enableSpeakerDiarization'
+          property :enable_word_confidence, as: 'enableWordConfidence'
+          property :filter_profanity, as: 'filterProfanity'
+          property :language_code, as: 'languageCode'
+          property :max_alternatives, as: 'maxAlternatives'
+          collection :speech_contexts, as: 'speechContexts', class: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1beta2SpeechContext, decorator: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1beta2SpeechContext::Representation
+      
+        end
+      end
+      
       class GoogleCloudVideointelligenceV1beta2VideoAnnotationProgress
         # @private
         class Representation < Google::Apis::Core::JsonRepresentation
@@ -637,6 +777,8 @@ module Google
       
           collection :shot_label_annotations, as: 'shotLabelAnnotations', class: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1beta2LabelAnnotation, decorator: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1beta2LabelAnnotation::Representation
       
+          collection :speech_transcriptions, as: 'speechTranscriptions', class: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1beta2SpeechTranscription, decorator: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1beta2SpeechTranscription::Representation
+      
         end
       end
       
@@ -651,6 +793,8 @@ module Google
       
           property :shot_change_detection_config, as: 'shotChangeDetectionConfig', class: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1beta2ShotChangeDetectionConfig, decorator: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1beta2ShotChangeDetectionConfig::Representation
       
+          property :speech_transcription_config, as: 'speechTranscriptionConfig', class: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1beta2SpeechTranscriptionConfig, decorator: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1beta2SpeechTranscriptionConfig::Representation
+      
         end
       end
       
@@ -662,6 +806,17 @@ module Google
         end
       end
       
+      class GoogleCloudVideointelligenceV1beta2WordInfo
+        # @private
+        class Representation < Google::Apis::Core::JsonRepresentation
+          property :confidence, as: 'confidence'
+          property :end_time, as: 'endTime'
+          property :speaker_tag, as: 'speakerTag'
+          property :start_time, as: 'startTime'
+          property :word, as: 'word'
+        end
+      end
+      
       class GoogleCloudVideointelligenceV1p1beta1AnnotateVideoProgress
         # @private
         class Representation < Google::Apis::Core::JsonRepresentation
@@ -749,6 +904,7 @@ module Google
         class Representation < Google::Apis::Core::JsonRepresentation
           collection :alternatives, as: 'alternatives', class: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1p1beta1SpeechRecognitionAlternative, decorator: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1p1beta1SpeechRecognitionAlternative::Representation
       
+          property :language_code, as: 'languageCode'
         end
       end
       
@@ -922,12 +1078,28 @@ module Google
         end
       end
       
-      class GoogleCloudVideointelligenceV1p2beta1TextAnnotation
+      class GoogleCloudVideointelligenceV1p2beta1SpeechRecognitionAlternative
         # @private
         class Representation < Google::Apis::Core::JsonRepresentation
           property :confidence, as: 'confidence'
-          collection :frames, as: 'frames', class: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1p2beta1TextFrame, decorator: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1p2beta1TextFrame::Representation
+          property :transcript, as: 'transcript'
+          collection :words, as: 'words', class: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1p2beta1WordInfo, decorator: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1p2beta1WordInfo::Representation
       
+        end
+      end
+      
+      class GoogleCloudVideointelligenceV1p2beta1SpeechTranscription
+        # @private
+        class Representation < Google::Apis::Core::JsonRepresentation
+          collection :alternatives, as: 'alternatives', class: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1p2beta1SpeechRecognitionAlternative, decorator: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1p2beta1SpeechRecognitionAlternative::Representation
+      
+          property :language_code, as: 'languageCode'
+        end
+      end
+      
+      class GoogleCloudVideointelligenceV1p2beta1TextAnnotation
+        # @private
+        class Representation < Google::Apis::Core::JsonRepresentation
           collection :segments, as: 'segments', class: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1p2beta1TextSegment, decorator: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1p2beta1TextSegment::Representation
       
           property :text, as: 'text'
@@ -946,6 +1118,9 @@ module Google
       class GoogleCloudVideointelligenceV1p2beta1TextSegment
         # @private
         class Representation < Google::Apis::Core::JsonRepresentation
+          property :confidence, as: 'confidence'
+          collection :frames, as: 'frames', class: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1p2beta1TextFrame, decorator: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1p2beta1TextFrame::Representation
+      
           property :segment, as: 'segment', class: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1p2beta1VideoSegment, decorator: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1p2beta1VideoSegment::Representation
       
         end
@@ -979,6 +1154,8 @@ module Google
       
           collection :shot_label_annotations, as: 'shotLabelAnnotations', class: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1p2beta1LabelAnnotation, decorator: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1p2beta1LabelAnnotation::Representation
       
+          collection :speech_transcriptions, as: 'speechTranscriptions', class: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1p2beta1SpeechTranscription, decorator: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1p2beta1SpeechTranscription::Representation
+      
           collection :text_annotations, as: 'textAnnotations', class: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1p2beta1TextAnnotation, decorator: Google::Apis::VideointelligenceV1beta2::GoogleCloudVideointelligenceV1p2beta1TextAnnotation::Representation
       
         end
@@ -992,6 +1169,17 @@ module Google
         end
       end
       
+      class GoogleCloudVideointelligenceV1p2beta1WordInfo
+        # @private
+        class Representation < Google::Apis::Core::JsonRepresentation
+          property :confidence, as: 'confidence'
+          property :end_time, as: 'endTime'
+          property :speaker_tag, as: 'speakerTag'
+          property :start_time, as: 'startTime'
+          property :word, as: 'word'
+        end
+      end
+      
       class GoogleLongrunningOperation
         # @private
         class Representation < Google::Apis::Core::JsonRepresentation

data/generated/google/apis/videointelligence_v1beta2/service.rb

@@ -22,7 +22,8 @@ module Google
     module VideointelligenceV1beta2
       # Cloud Video Intelligence API
       #
-      # Cloud Video Intelligence API.
+      # Detects objects, explicit content, and scene changes in videos. It also
+      #  specifies the region for annotation and transcribes speech to text.
       #
       # @example
       #    require 'google/apis/videointelligence_v1beta2'

data/generated/google/apis/videointelligence_v1p1beta1.rb

@@ -20,12 +20,13 @@ module Google
   module Apis
     # Cloud Video Intelligence API
     #
-    # Cloud Video Intelligence API.
+    # Detects objects, explicit content, and scene changes in videos. It also
+    # specifies the region for annotation and transcribes speech to text.
     #
     # @see https://cloud.google.com/video-intelligence/docs/
     module VideointelligenceV1p1beta1
       VERSION = 'V1p1beta1'
-      REVISION = '20180920'
+      REVISION = '20181027'
 
       # View and manage your data across Google Cloud Platform services
       AUTH_CLOUD_PLATFORM = 'https://www.googleapis.com/auth/cloud-platform'

data/generated/google/apis/videointelligence_v1p1beta1/classes.rb

@@ -235,6 +235,73 @@ module Google
         end
       end
       
+      # Alternative hypotheses (a.k.a. n-best list).
+      class GoogleCloudVideointelligenceV1SpeechRecognitionAlternative
+        include Google::Apis::Core::Hashable
+      
+        # 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.
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
+      
+        # Transcript text representing the words that the user spoke.
+        # Corresponds to the JSON property `transcript`
+        # @return [String]
+        attr_accessor :transcript
+      
+        # A list of word-specific information for each recognized word.
+        # Corresponds to the JSON property `words`
+        # @return [Array<Google::Apis::VideointelligenceV1p1beta1::GoogleCloudVideointelligenceV1WordInfo>]
+        attr_accessor :words
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @transcript = args[:transcript] if args.key?(:transcript)
+          @words = args[:words] if args.key?(:words)
+        end
+      end
+      
+      # A speech recognition result corresponding to a portion of the audio.
+      class GoogleCloudVideointelligenceV1SpeechTranscription
+        include Google::Apis::Core::Hashable
+      
+        # 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.
+        # Corresponds to the JSON property `alternatives`
+        # @return [Array<Google::Apis::VideointelligenceV1p1beta1::GoogleCloudVideointelligenceV1SpeechRecognitionAlternative>]
+        attr_accessor :alternatives
+      
+        # 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.
+        # Corresponds to the JSON property `languageCode`
+        # @return [String]
+        attr_accessor :language_code
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @alternatives = args[:alternatives] if args.key?(:alternatives)
+          @language_code = args[:language_code] if args.key?(:language_code)
+        end
+      end
+      
       # Annotation progress for a single video.
       class GoogleCloudVideointelligenceV1VideoAnnotationProgress
         include Google::Apis::Core::Hashable
@@ -357,6 +424,11 @@ module Google
         # @return [Array<Google::Apis::VideointelligenceV1p1beta1::GoogleCloudVideointelligenceV1LabelAnnotation>]
         attr_accessor :shot_label_annotations
       
+        # Speech transcription.
+        # Corresponds to the JSON property `speechTranscriptions`
+        # @return [Array<Google::Apis::VideointelligenceV1p1beta1::GoogleCloudVideointelligenceV1SpeechTranscription>]
+        attr_accessor :speech_transcriptions
+      
         def initialize(**args)
            update!(**args)
         end
@@ -370,6 +442,7 @@ module Google
           @segment_label_annotations = args[:segment_label_annotations] if args.key?(:segment_label_annotations)
           @shot_annotations = args[:shot_annotations] if args.key?(:shot_annotations)
           @shot_label_annotations = args[:shot_label_annotations] if args.key?(:shot_label_annotations)
+          @speech_transcriptions = args[:speech_transcriptions] if args.key?(:speech_transcriptions)
         end
       end
       
@@ -400,6 +473,65 @@ module Google
         end
       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`.
+      class GoogleCloudVideointelligenceV1WordInfo
+        include Google::Apis::Core::Hashable
+      
+        # 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.
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
+      
+        # 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.
+        # Corresponds to the JSON property `endTime`
+        # @return [String]
+        attr_accessor :end_time
+      
+        # 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.
+        # Corresponds to the JSON property `speakerTag`
+        # @return [Fixnum]
+        attr_accessor :speaker_tag
+      
+        # 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.
+        # Corresponds to the JSON property `startTime`
+        # @return [String]
+        attr_accessor :start_time
+      
+        # The word corresponding to this set of information.
+        # Corresponds to the JSON property `word`
+        # @return [String]
+        attr_accessor :word
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @end_time = args[:end_time] if args.key?(:end_time)
+          @speaker_tag = args[:speaker_tag] if args.key?(:speaker_tag)
+          @start_time = args[:start_time] if args.key?(:start_time)
+          @word = args[:word] if args.key?(:word)
+        end
+      end
+      
       # Video annotation progress. Included in the `metadata`
       # field of the `Operation` returned by the `GetOperation`
       # call of the `google::longrunning::Operations` service.
@@ -613,6 +745,73 @@ module Google
         end
       end
       
+      # Alternative hypotheses (a.k.a. n-best list).
+      class GoogleCloudVideointelligenceV1beta2SpeechRecognitionAlternative
+        include Google::Apis::Core::Hashable
+      
+        # 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.
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
+      
+        # Transcript text representing the words that the user spoke.
+        # Corresponds to the JSON property `transcript`
+        # @return [String]
+        attr_accessor :transcript
+      
+        # A list of word-specific information for each recognized word.
+        # Corresponds to the JSON property `words`
+        # @return [Array<Google::Apis::VideointelligenceV1p1beta1::GoogleCloudVideointelligenceV1beta2WordInfo>]
+        attr_accessor :words
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @transcript = args[:transcript] if args.key?(:transcript)
+          @words = args[:words] if args.key?(:words)
+        end
+      end
+      
+      # A speech recognition result corresponding to a portion of the audio.
+      class GoogleCloudVideointelligenceV1beta2SpeechTranscription
+        include Google::Apis::Core::Hashable
+      
+        # 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.
+        # Corresponds to the JSON property `alternatives`
+        # @return [Array<Google::Apis::VideointelligenceV1p1beta1::GoogleCloudVideointelligenceV1beta2SpeechRecognitionAlternative>]
+        attr_accessor :alternatives
+      
+        # 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.
+        # Corresponds to the JSON property `languageCode`
+        # @return [String]
+        attr_accessor :language_code
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @alternatives = args[:alternatives] if args.key?(:alternatives)
+          @language_code = args[:language_code] if args.key?(:language_code)
+        end
+      end
+      
       # Annotation progress for a single video.
       class GoogleCloudVideointelligenceV1beta2VideoAnnotationProgress
         include Google::Apis::Core::Hashable
@@ -735,6 +934,11 @@ module Google
         # @return [Array<Google::Apis::VideointelligenceV1p1beta1::GoogleCloudVideointelligenceV1beta2LabelAnnotation>]
         attr_accessor :shot_label_annotations
       
+        # Speech transcription.
+        # Corresponds to the JSON property `speechTranscriptions`
+        # @return [Array<Google::Apis::VideointelligenceV1p1beta1::GoogleCloudVideointelligenceV1beta2SpeechTranscription>]
+        attr_accessor :speech_transcriptions
+      
         def initialize(**args)
            update!(**args)
         end
@@ -748,6 +952,7 @@ module Google
           @segment_label_annotations = args[:segment_label_annotations] if args.key?(:segment_label_annotations)
           @shot_annotations = args[:shot_annotations] if args.key?(:shot_annotations)
           @shot_label_annotations = args[:shot_label_annotations] if args.key?(:shot_label_annotations)
+          @speech_transcriptions = args[:speech_transcriptions] if args.key?(:speech_transcriptions)
         end
       end
       
@@ -778,6 +983,65 @@ module Google
         end
       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`.
+      class GoogleCloudVideointelligenceV1beta2WordInfo
+        include Google::Apis::Core::Hashable
+      
+        # 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.
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
+      
+        # 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.
+        # Corresponds to the JSON property `endTime`
+        # @return [String]
+        attr_accessor :end_time
+      
+        # 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.
+        # Corresponds to the JSON property `speakerTag`
+        # @return [Fixnum]
+        attr_accessor :speaker_tag
+      
+        # 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.
+        # Corresponds to the JSON property `startTime`
+        # @return [String]
+        attr_accessor :start_time
+      
+        # The word corresponding to this set of information.
+        # Corresponds to the JSON property `word`
+        # @return [String]
+        attr_accessor :word
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @end_time = args[:end_time] if args.key?(:end_time)
+          @speaker_tag = args[:speaker_tag] if args.key?(:speaker_tag)
+          @start_time = args[:start_time] if args.key?(:start_time)
+          @word = args[:word] if args.key?(:word)
+        end
+      end
+      
       # Video annotation progress. Included in the `metadata`
       # field of the `Operation` returned by the `GetOperation`
       # call of the `google::longrunning::Operations` service.
@@ -1212,6 +1476,14 @@ module Google
         # @return [Array<Google::Apis::VideointelligenceV1p1beta1::GoogleCloudVideointelligenceV1p1beta1SpeechRecognitionAlternative>]
         attr_accessor :alternatives
       
+        # 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.
+        # Corresponds to the JSON property `languageCode`
+        # @return [String]
+        attr_accessor :language_code
+      
         def initialize(**args)
            update!(**args)
         end
@@ -1219,6 +1491,7 @@ module Google
         # Update properties of this object
         def update!(**args)
           @alternatives = args[:alternatives] if args.key?(:alternatives)
+          @language_code = args[:language_code] if args.key?(:language_code)
         end
       end
       
@@ -1291,7 +1564,7 @@ module Google
       
         # *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
+        # 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.
         # Corresponds to the JSON property `maxAlternatives`
@@ -1973,22 +2246,78 @@ module Google
         end
       end
       
-      # Annotations related to one detected OCR text snippet. This will contain the
-      # corresponding text, confidence value, and frame level information for each
-      # detection.
-      class GoogleCloudVideointelligenceV1p2beta1TextAnnotation
+      # Alternative hypotheses (a.k.a. n-best list).
+      class GoogleCloudVideointelligenceV1p2beta1SpeechRecognitionAlternative
         include Google::Apis::Core::Hashable
       
-        # Confidence for the track of detected text. It is calculated as the highest
-        # over all frames where OCR detected text appears.
+        # 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.
         # Corresponds to the JSON property `confidence`
         # @return [Float]
         attr_accessor :confidence
       
-        # Information related to the frames where OCR detected text appears.
-        # Corresponds to the JSON property `frames`
-        # @return [Array<Google::Apis::VideointelligenceV1p1beta1::GoogleCloudVideointelligenceV1p2beta1TextFrame>]
-        attr_accessor :frames
+        # Transcript text representing the words that the user spoke.
+        # Corresponds to the JSON property `transcript`
+        # @return [String]
+        attr_accessor :transcript
+      
+        # A list of word-specific information for each recognized word.
+        # Corresponds to the JSON property `words`
+        # @return [Array<Google::Apis::VideointelligenceV1p1beta1::GoogleCloudVideointelligenceV1p2beta1WordInfo>]
+        attr_accessor :words
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @transcript = args[:transcript] if args.key?(:transcript)
+          @words = args[:words] if args.key?(:words)
+        end
+      end
+      
+      # A speech recognition result corresponding to a portion of the audio.
+      class GoogleCloudVideointelligenceV1p2beta1SpeechTranscription
+        include Google::Apis::Core::Hashable
+      
+        # 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.
+        # Corresponds to the JSON property `alternatives`
+        # @return [Array<Google::Apis::VideointelligenceV1p1beta1::GoogleCloudVideointelligenceV1p2beta1SpeechRecognitionAlternative>]
+        attr_accessor :alternatives
+      
+        # 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.
+        # Corresponds to the JSON property `languageCode`
+        # @return [String]
+        attr_accessor :language_code
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @alternatives = args[:alternatives] if args.key?(:alternatives)
+          @language_code = args[:language_code] if args.key?(:language_code)
+        end
+      end
+      
+      # Annotations related to one detected OCR text snippet. This will contain the
+      # corresponding text, confidence value, and frame level information for each
+      # detection.
+      class GoogleCloudVideointelligenceV1p2beta1TextAnnotation
+        include Google::Apis::Core::Hashable
       
         # All video segments where OCR detected text appears.
         # Corresponds to the JSON property `segments`
@@ -2006,8 +2335,6 @@ module Google
       
         # Update properties of this object
         def update!(**args)
-          @confidence = args[:confidence] if args.key?(:confidence)
-          @frames = args[:frames] if args.key?(:frames)
           @segments = args[:segments] if args.key?(:segments)
           @text = args[:text] if args.key?(:text)
         end
@@ -2058,6 +2385,17 @@ module Google
       class GoogleCloudVideointelligenceV1p2beta1TextSegment
         include Google::Apis::Core::Hashable
       
+        # Confidence for the track of detected text. It is calculated as the highest
+        # over all frames where OCR detected text appears.
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
+      
+        # Information related to the frames where OCR detected text appears.
+        # Corresponds to the JSON property `frames`
+        # @return [Array<Google::Apis::VideointelligenceV1p1beta1::GoogleCloudVideointelligenceV1p2beta1TextFrame>]
+        attr_accessor :frames
+      
         # Video segment.
         # Corresponds to the JSON property `segment`
         # @return [Google::Apis::VideointelligenceV1p1beta1::GoogleCloudVideointelligenceV1p2beta1VideoSegment]
@@ -2069,6 +2407,8 @@ module Google
       
         # Update properties of this object
         def update!(**args)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @frames = args[:frames] if args.key?(:frames)
           @segment = args[:segment] if args.key?(:segment)
         end
       end
@@ -2200,6 +2540,11 @@ module Google
         # @return [Array<Google::Apis::VideointelligenceV1p1beta1::GoogleCloudVideointelligenceV1p2beta1LabelAnnotation>]
         attr_accessor :shot_label_annotations
       
+        # Speech transcription.
+        # Corresponds to the JSON property `speechTranscriptions`
+        # @return [Array<Google::Apis::VideointelligenceV1p1beta1::GoogleCloudVideointelligenceV1p2beta1SpeechTranscription>]
+        attr_accessor :speech_transcriptions
+      
         # OCR text detection and tracking.
         # Annotations for list of detected text snippets. Each will have list of
         # frame information associated with it.
@@ -2221,6 +2566,7 @@ module Google
           @segment_label_annotations = args[:segment_label_annotations] if args.key?(:segment_label_annotations)
           @shot_annotations = args[:shot_annotations] if args.key?(:shot_annotations)
           @shot_label_annotations = args[:shot_label_annotations] if args.key?(:shot_label_annotations)
+          @speech_transcriptions = args[:speech_transcriptions] if args.key?(:speech_transcriptions)
           @text_annotations = args[:text_annotations] if args.key?(:text_annotations)
         end
       end
@@ -2252,6 +2598,65 @@ module Google
         end
       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`.
+      class GoogleCloudVideointelligenceV1p2beta1WordInfo
+        include Google::Apis::Core::Hashable
+      
+        # 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.
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
+      
+        # 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.
+        # Corresponds to the JSON property `endTime`
+        # @return [String]
+        attr_accessor :end_time
+      
+        # 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.
+        # Corresponds to the JSON property `speakerTag`
+        # @return [Fixnum]
+        attr_accessor :speaker_tag
+      
+        # 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.
+        # Corresponds to the JSON property `startTime`
+        # @return [String]
+        attr_accessor :start_time
+      
+        # The word corresponding to this set of information.
+        # Corresponds to the JSON property `word`
+        # @return [String]
+        attr_accessor :word
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @end_time = args[:end_time] if args.key?(:end_time)
+          @speaker_tag = args[:speaker_tag] if args.key?(:speaker_tag)
+          @start_time = args[:start_time] if args.key?(:start_time)
+          @word = args[:word] if args.key?(:word)
+        end
+      end
+      
       # This resource represents a long-running operation that is the result of a
       # network API call.
       class GoogleLongrunningOperation