Type Alias TranscriptionConfig

TranscriptionConfig: {
    adaptation_phrases?: string[];
    custom_vocabulary?: string[];
    diarization_mode?: string;
    language_codes?: string[];
    timestamp_granularities?: string[];
}

Configuration for speech recognition (transcription).

Type declaration

  • Optionaladaptation_phrases?: string[]

    Optional. A list of phrases to bias the ASR model towards.

    Deprecated

    field: This will be removed in a future release, please migrate away from it as soon as possible.

  • Optionalcustom_vocabulary?: string[]

    Optional. A list of custom vocabulary phrases to bias the speech recognition model

    Remarks

    toward recognizing specific terms.

  • Optionaldiarization_mode?: string

    Optional. Configures speaker diarization. Supported values: "speaker".

  • Optionallanguage_codes?: string[]

    Optional. BCP-47 language codes providing hints about the languages present in the

    Remarks

    audio. If omitted or empty, defaults to automatic language detection.

  • Optionaltimestamp_granularities?: string[]

    Optional. The granularity of timestamps to include in the transcription output.

    Remarks

    Supported values: "word". If empty, no timestamps are generated.

Settings