Documentation

Settings specific to the Amazon Transcribe engine.

See: newEngineTranscribeSettings smart constructor.

Create a value of EngineTranscribeSettings 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:contentIdentificationType:EngineTranscribeSettings', engineTranscribeSettings_contentIdentificationType - Set this field to PII to identify personally identifiable information in the transcription output.

$sel:contentRedactionType:EngineTranscribeSettings', engineTranscribeSettings_contentRedactionType - Set this field to PII to redact personally identifiable information in the transcription output. Content redaction is performed only upon complete transcription of the audio segments.

You can’t set ContentRedactionType and ContentIdentificationType in the same request. If you set both, your request returns a BadRequestException.

$sel:enablePartialResultsStabilization:EngineTranscribeSettings', engineTranscribeSettings_enablePartialResultsStabilization - Generates partial transcription results that are less likely to change as meeting attendees speak. It does so by only allowing the last few words from the partial results to change.

$sel:identifyLanguage:EngineTranscribeSettings', engineTranscribeSettings_identifyLanguage - Automatically identifies the language spoken in media files.

$sel:languageCode:EngineTranscribeSettings', engineTranscribeSettings_languageCode - The language code specified for the Amazon Transcribe engine.

$sel:languageModelName:EngineTranscribeSettings', engineTranscribeSettings_languageModelName - The name of the language model used during transcription.

$sel:languageOptions:EngineTranscribeSettings', engineTranscribeSettings_languageOptions - Language codes for the languages that you want to identify. You must provide at least 2 codes.

$sel:partialResultsStability:EngineTranscribeSettings', engineTranscribeSettings_partialResultsStability - The stabity level of a partial results transcription. Determines how stable you want the transcription results to be. A higher level means the transcription results are less likely to change.

$sel:piiEntityTypes:EngineTranscribeSettings', engineTranscribeSettings_piiEntityTypes - Lists the PII entity types you want to identify or redact. To specify entity types, you must enable ContentIdentificationType or ContentRedactionType.

PIIEntityTypes must be comma-separated. The available values are: BANK_ACCOUNT_NUMBER, BANK_ROUTING, CREDIT_DEBIT_NUMBER, CREDIT_DEBIT_CVV, CREDIT_DEBIT_EXPIRY, PIN, EMAIL, ADDRESS, NAME, PHONE, SSN, and ALL.

PiiEntityTypes is an optional parameter with a default value of ALL.

$sel:preferredLanguage:EngineTranscribeSettings', engineTranscribeSettings_preferredLanguage - Language code for the preferred language.

$sel:region:EngineTranscribeSettings', engineTranscribeSettings_region - The AWS Region passed to Amazon Transcribe. If you don't specify a Region, Amazon Chime uses the meeting's Region.

$sel:vocabularyFilterMethod:EngineTranscribeSettings', engineTranscribeSettings_vocabularyFilterMethod - The filtering method passed to Amazon Transcribe.

$sel:vocabularyFilterName:EngineTranscribeSettings', engineTranscribeSettings_vocabularyFilterName - The name of the vocabulary filter passed to Amazon Transcribe.

$sel:vocabularyName:EngineTranscribeSettings', engineTranscribeSettings_vocabularyName - The name of the vocabulary passed to Amazon Transcribe.

Set this field to PII to identify personally identifiable information in the transcription output.

Set this field to PII to redact personally identifiable information in the transcription output. Content redaction is performed only upon complete transcription of the audio segments.

You can’t set ContentRedactionType and ContentIdentificationType in the same request. If you set both, your request returns a BadRequestException.

Generates partial transcription results that are less likely to change as meeting attendees speak. It does so by only allowing the last few words from the partial results to change.

Automatically identifies the language spoken in media files.

The language code specified for the Amazon Transcribe engine.

The name of the language model used during transcription.

Language codes for the languages that you want to identify. You must provide at least 2 codes.

The stabity level of a partial results transcription. Determines how stable you want the transcription results to be. A higher level means the transcription results are less likely to change.

Lists the PII entity types you want to identify or redact. To specify entity types, you must enable ContentIdentificationType or ContentRedactionType.

PIIEntityTypes must be comma-separated. The available values are: BANK_ACCOUNT_NUMBER, BANK_ROUTING, CREDIT_DEBIT_NUMBER, CREDIT_DEBIT_CVV, CREDIT_DEBIT_EXPIRY, PIN, EMAIL, ADDRESS, NAME, PHONE, SSN, and ALL.

PiiEntityTypes is an optional parameter with a default value of ALL.

Language code for the preferred language.

The AWS Region passed to Amazon Transcribe. If you don't specify a Region, Amazon Chime uses the meeting's Region.

The filtering method passed to Amazon Transcribe.

The name of the vocabulary filter passed to Amazon Transcribe.

The name of the vocabulary passed to Amazon Transcribe.