Amazon Chime

2021/11/18 - Amazon Chime - 1 updated api methods

Changes  Adds new Transcribe API parameters to StartMeetingTranscription, including support for content identification and redaction (PII & PHI), partial results stabilization, and custom language models.

StartMeetingTranscription (updated) Link ΒΆ
Changes (request)
{'TranscriptionConfiguration': {'EngineTranscribeMedicalSettings': {'ContentIdentificationType': 'PHI'},
                                'EngineTranscribeSettings': {'ContentIdentificationType': 'PII',
                                                             'ContentRedactionType': 'PII',
                                                             'EnablePartialResultsStabilization': 'boolean',
                                                             'LanguageModelName': 'string',
                                                             'PartialResultsStability': 'low '
                                                                                        '| '
                                                                                        'medium '
                                                                                        '| '
                                                                                        'high',
                                                             'PiiEntityTypes': 'string'}}}

Starts transcription for the specified meetingId .

See also: AWS API Documentation

Request Syntax

client.start_meeting_transcription(
    MeetingId='string',
    TranscriptionConfiguration={
        'EngineTranscribeSettings': {
            'LanguageCode': 'en-US'|'en-GB'|'es-US'|'fr-CA'|'fr-FR'|'en-AU'|'it-IT'|'de-DE'|'pt-BR'|'ja-JP'|'ko-KR'|'zh-CN',
            'VocabularyFilterMethod': 'remove'|'mask'|'tag',
            'VocabularyFilterName': 'string',
            'VocabularyName': 'string',
            'Region': 'us-east-2'|'us-east-1'|'us-west-2'|'ap-northeast-2'|'ap-southeast-2'|'ap-northeast-1'|'ca-central-1'|'eu-central-1'|'eu-west-1'|'eu-west-2'|'sa-east-1'|'auto',
            'EnablePartialResultsStabilization': True|False,
            'PartialResultsStability': 'low'|'medium'|'high',
            'ContentIdentificationType': 'PII',
            'ContentRedactionType': 'PII',
            'PiiEntityTypes': 'string',
            'LanguageModelName': 'string'
        },
        'EngineTranscribeMedicalSettings': {
            'LanguageCode': 'en-US',
            'Specialty': 'PRIMARYCARE'|'CARDIOLOGY'|'NEUROLOGY'|'ONCOLOGY'|'RADIOLOGY'|'UROLOGY',
            'Type': 'CONVERSATION'|'DICTATION',
            'VocabularyName': 'string',
            'Region': 'us-east-1'|'us-east-2'|'us-west-2'|'ap-southeast-2'|'ca-central-1'|'eu-west-1'|'auto',
            'ContentIdentificationType': 'PHI'
        }
    }
)
type MeetingId

string

param MeetingId

[REQUIRED]

The unique ID of the meeting being transcribed.

type TranscriptionConfiguration

dict

param TranscriptionConfiguration

[REQUIRED]

The configuration for the current transcription operation. Must contain EngineTranscribeSettings or EngineTranscribeMedicalSettings .

  • EngineTranscribeSettings (dict) --

    The transcription configuration settings passed to Amazon Transcribe.

    • LanguageCode (string) -- [REQUIRED]

      The language code specified for the Amazon Transcribe engine.

    • VocabularyFilterMethod (string) --

      The filtering method passed to Amazon Transcribe.

    • VocabularyFilterName (string) --

      The name of the vocabulary filter passed to Amazon Transcribe.

    • VocabularyName (string) --

      The name of the vocabulary passed to Amazon Transcribe.

    • Region (string) --

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

    • EnablePartialResultsStabilization (boolean) --

      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.

    • PartialResultsStability (string) --

      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.

    • ContentIdentificationType (string) --

      Set this field to PII to identify personal health information in the transcription output.

    • ContentRedactionType (string) --

      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.

    • PiiEntityTypes (string) --

      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 .

    • LanguageModelName (string) --

      The name of the language model used during transcription.

  • EngineTranscribeMedicalSettings (dict) --

    The transcription configuration settings passed to Amazon Transcribe Medical.

    • LanguageCode (string) -- [REQUIRED]

      The language code specified for the Amazon Transcribe Medical engine.

    • Specialty (string) -- [REQUIRED]

      The specialty specified for the Amazon Transcribe Medical engine.

    • Type (string) -- [REQUIRED]

      The type of transcription.

    • VocabularyName (string) --

      The name of the vocabulary passed to Amazon Transcribe Medical.

    • Region (string) --

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

    • ContentIdentificationType (string) --

      Set this field to PHI to identify personal health information in the transcription output.

rtype

dict

returns

Response Syntax

{}

Response Structure

  • (dict) --