- release_tracks: [ALPHA, BETA]

  help_text:
    brief: Transcribe speech in a video.
    description: |
      Transcribe speech within a video.
    examples: |
      To transcribe speech in video file 'gs://my_bucket/input_file.mp4':

        $ {command} gs://my_bucket/input_file.mp4
  request:
    _COMMON_: request
    static_fields:
      features: [SPEECH_TRANSCRIPTION]
    modify_request_hooks:
    - googlecloudsdk.command_lib.ml.video.util:UpdateRequestWithInput

  async:
    _COMMON_: async

  arguments:
    params:
    - _COMMON_args
    - api_field: videoContext.speechTranscriptionConfig.enableAutomaticPunctuation
      arg_name: enable-automatic-punctuation
      help_text: |
        If enabled, 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 disabled case does not add punctuation to result hypotheses.
    - api_field: videoContext.speechTranscriptionConfig.enableSpeakerDiarization
      arg_name: enable-speaker-diarization
      help_text: |
        If enabled, perform speaker detection for each recognized word in the top alternative of the
        recognition result using a speaker_tag provided in the WordInfo results section. When this
        is enabled, 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.
    - api_field: videoContext.speechTranscriptionConfig.diarizationSpeakerCount
      arg_name: diarization-speaker-count
      help_text: |
        Optional estimated number of speakers in the conversation. If not specified, defaults to
        '2'. Ignored unless --enable-speaker-diarization is enabled.
    - api_field: videoContext.speechTranscriptionConfig.maxAlternatives
      arg_name: max-alternatives
      help_text: |
        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
    - api_field: videoContext.speechTranscriptionConfig.languageCode
      arg_name: language-code
      required: true
      help_text: |
          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.
    - api_field: videoContext.speechTranscriptionConfig.filterProfanity
      arg_name: filter-profanity
      help_text: |
        If enabled, the server will attempt to filter out profanities, replacing all but the
        initial character in each filtered word with asterisks, e.g. ```f***```. If disabled or
        omitted, profanities will not be filtered out.
    - api_field: videoContext.speechTranscriptionConfig.enableWordConfidence
      arg_name: enable-word-confidence
      help_text: |
        If enabled, the top result includes a list of words and the confidence for those words. If
        disabled, no word-level confidence information is returned. The default is disabled.
    - api_field: videoContext.speechTranscriptionConfig.audioTracks
      arg_name: audio-tracks
      processor: googlecloudsdk.command_lib.ml.video.util:AudioTrackProcessor
      help_text: |
        For file formats, such as MXF or MKV, supporting multiple audio tracks, specify up to two
        commas separated tracks. Default track is 0.
    - api_field: videoContext.speechTranscriptionConfig.speechContexts.phrases
      arg_name: hints
      default: []
      help_text: |
        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
        (https://cloud.google.com/speech/limits#content).
  output:
    format: yaml