Documentation

Allows additional optional settings in your request, including channel identification, alternative transcriptions, and speaker partitioning. You can use that to apply custom vocabularies to your transcription job.

See: newSettings smart constructor.

Create a value of Settings with all optional fields omitted.

Use generic-lens or optics to modify other optional fields.

The following record fields are available, with the corresponding lenses provided for backwards compatibility:

$sel:channelIdentification:Settings', settings_channelIdentification - Enables channel identification in multi-channel audio.

Channel identification transcribes the audio on each channel independently, then appends the output for each channel into one transcript.

You can't include both ShowSpeakerLabels and ChannelIdentification in the same request. Including both parameters returns a BadRequestException.

For more information, see Transcribing multi-channel audio.

$sel:maxAlternatives:Settings', settings_maxAlternatives - Indicate the maximum number of alternative transcriptions you want Amazon Transcribe to include in your transcript.

If you select a number greater than the number of alternative transcriptions generated by Amazon Transcribe, only the actual number of alternative transcriptions are included.

If you include MaxAlternatives in your request, you must also include ShowAlternatives with a value of true.

For more information, see Alternative transcriptions.

$sel:maxSpeakerLabels:Settings', settings_maxSpeakerLabels - Specify the maximum number of speakers you want to partition in your media.

Note that if your media contains more speakers than the specified number, multiple speakers are treated as a single speaker.

If you specify the MaxSpeakerLabels field, you must set the ShowSpeakerLabels field to true.

$sel:showAlternatives:Settings', settings_showAlternatives - To include alternative transcriptions within your transcription output, include ShowAlternatives in your transcription request.

If you have multi-channel audio and do not enable channel identification, your audio is transcribed in a continuous manner and your transcript does not separate the speech by channel.

If you include ShowAlternatives, you must also include MaxAlternatives, which is the maximum number of alternative transcriptions you want Amazon Transcribe to generate.

For more information, see Alternative transcriptions.

$sel:showSpeakerLabels:Settings', settings_showSpeakerLabels - Enables speaker partitioning (diarization) in your transcription output. Speaker partitioning labels the speech from individual speakers in your media file.

If you enable ShowSpeakerLabels in your request, you must also include MaxSpeakerLabels.

You can't include both ShowSpeakerLabels and ChannelIdentification in the same request. Including both parameters returns a BadRequestException.

For more information, see Partitioning speakers (diarization).

$sel:vocabularyFilterMethod:Settings', settings_vocabularyFilterMethod - Specify how you want your custom vocabulary filter applied to your transcript.

To replace words with ***, choose mask.

To delete words, choose remove.

To flag words without changing them, choose tag.

$sel:vocabularyFilterName:Settings', settings_vocabularyFilterName - The name of the custom vocabulary filter you want to use in your transcription job request. This name is case sensitive, cannot contain spaces, and must be unique within an Amazon Web Services account.

Note that if you include VocabularyFilterName in your request, you must also include VocabularyFilterMethod.

$sel:vocabularyName:Settings', settings_vocabularyName - The name of the custom vocabulary you want to use in your transcription job request. This name is case sensitive, cannot contain spaces, and must be unique within an Amazon Web Services account.

Enables channel identification in multi-channel audio.

Channel identification transcribes the audio on each channel independently, then appends the output for each channel into one transcript.

You can't include both ShowSpeakerLabels and ChannelIdentification in the same request. Including both parameters returns a BadRequestException.

For more information, see Transcribing multi-channel audio.

Indicate the maximum number of alternative transcriptions you want Amazon Transcribe to include in your transcript.

If you select a number greater than the number of alternative transcriptions generated by Amazon Transcribe, only the actual number of alternative transcriptions are included.

If you include MaxAlternatives in your request, you must also include ShowAlternatives with a value of true.

For more information, see Alternative transcriptions.

Specify the maximum number of speakers you want to partition in your media.

Note that if your media contains more speakers than the specified number, multiple speakers are treated as a single speaker.

If you specify the MaxSpeakerLabels field, you must set the ShowSpeakerLabels field to true.

To include alternative transcriptions within your transcription output, include ShowAlternatives in your transcription request.

If you have multi-channel audio and do not enable channel identification, your audio is transcribed in a continuous manner and your transcript does not separate the speech by channel.

If you include ShowAlternatives, you must also include MaxAlternatives, which is the maximum number of alternative transcriptions you want Amazon Transcribe to generate.

For more information, see Alternative transcriptions.

Enables speaker partitioning (diarization) in your transcription output. Speaker partitioning labels the speech from individual speakers in your media file.

If you enable ShowSpeakerLabels in your request, you must also include MaxSpeakerLabels.

You can't include both ShowSpeakerLabels and ChannelIdentification in the same request. Including both parameters returns a BadRequestException.

For more information, see Partitioning speakers (diarization).

Specify how you want your custom vocabulary filter applied to your transcript.

To replace words with ***, choose mask.

To delete words, choose remove.

To flag words without changing them, choose tag.

The name of the custom vocabulary filter you want to use in your transcription job request. This name is case sensitive, cannot contain spaces, and must be unique within an Amazon Web Services account.

Note that if you include VocabularyFilterName in your request, you must also include VocabularyFilterMethod.

The name of the custom vocabulary you want to use in your transcription job request. This name is case sensitive, cannot contain spaces, and must be unique within an Amazon Web Services account.