Share via


TranscriptionOptions interface

Metadata for a transcription request.

Properties

activeChannels

The 0-based indices of the channels to be transcribed separately. If not specified, multiple channels are merged and transcribed jointly. Only up to two channels are supported.

audioUrl

The URL of the audio to be transcribed. The audio must be shorter than 2 hours in audio duration and smaller than 250 MB in size. If both Audio and AudioUrl are provided, Audio is used.

diarizationOptions

Mode of diarization.

enhancedMode

Enhanced mode properties.

locales

A list of possible locales for the transcription. If not specified, the locale of the speech in the audio is detected automatically from all supported locales.

models

Maps some or all candidate locales to a model URI to be used for transcription. If no mapping is given, the default model for the locale is used.

phraseList

Phrase list properties.

profanityFilterMode

Mode of profanity filtering.

Property Details

activeChannels

The 0-based indices of the channels to be transcribed separately. If not specified, multiple channels are merged and transcribed jointly. Only up to two channels are supported.

activeChannels?: number[]

Property Value

number[]

audioUrl

The URL of the audio to be transcribed. The audio must be shorter than 2 hours in audio duration and smaller than 250 MB in size. If both Audio and AudioUrl are provided, Audio is used.

audioUrl?: string

Property Value

string

diarizationOptions

Mode of diarization.

diarizationOptions?: TranscriptionDiarizationOptions

Property Value

enhancedMode

Enhanced mode properties.

enhancedMode?: EnhancedModeOptions

Property Value

locales

A list of possible locales for the transcription. If not specified, the locale of the speech in the audio is detected automatically from all supported locales.

locales?: string[]

Property Value

string[]

models

Maps some or all candidate locales to a model URI to be used for transcription. If no mapping is given, the default model for the locale is used.

models?: Record<string, string>

Property Value

Record<string, string>

phraseList

Phrase list properties.

phraseList?: PhraseListOptions

Property Value

profanityFilterMode

Mode of profanity filtering.

profanityFilterMode?: string

Property Value

string