aws_transcribe_call_analytics_job

account_id

Type: STRING

call_analytics_job_details

Type: STRUCT
Provider name: CallAnalyticsJobDetails
Description: Provides detailed information about a call analytics job, including information about skipped analytics features.

• skipped
  Type: UNORDERED_LIST_STRUCT
  Provider name: Skipped
  Description: Contains information about any skipped analytics features during the analysis of a call analytics job. This array lists all the analytics features that were skipped, along with their corresponding reason code and message.
  
  • feature
    Type: STRING
    Provider name: Feature
    Description: Indicates the type of analytics feature that was skipped during the analysis of a call analytics job.
    
  • message
    Type: STRING
    Provider name: Message
    Description: Contains additional information or a message explaining why a specific analytics feature was skipped during the analysis of a call analytics job.
    
  • reason_code
    Type: STRING
    Provider name: ReasonCode
    Description: Provides a code indicating the reason why a specific analytics feature was skipped during the analysis of a call analytics job.
    

call_analytics_job_name

Type: STRING
Provider name: CallAnalyticsJobName
Description: The name of the Call Analytics job. Job names are case sensitive and must be unique within an Amazon Web Services account.

call_analytics_job_status

Type: STRING
Provider name: CallAnalyticsJobStatus
Description: Provides the status of the specified Call Analytics job. If the status is COMPLETED, the job is finished and you can find the results at the location specified in TranscriptFileUri (or RedactedTranscriptFileUri, if you requested transcript redaction). If the status is FAILED, FailureReason provides details on why your transcription job failed.

channel_definitions

Type: UNORDERED_LIST_STRUCT
Provider name: ChannelDefinitions
Description: Indicates which speaker is on which channel.

• channel_id
  Type: INT32
  Provider name: ChannelId
  Description: Specify the audio channel you want to define.
  
• participant_role
  Type: STRING
  Provider name: ParticipantRole
  Description: Specify the speaker you want to define. Omitting this parameter is equivalent to specifying both participants.
  

completion_time

Type: TIMESTAMP
Provider name: CompletionTime
Description: The date and time the specified Call Analytics job finished processing. Timestamps are in the format YYYY-MM-DD’T’HH:MM:SS.SSSSSS-UTC. For example, 2022-05-04T12:33:13.922000-07:00 represents a transcription job that started processing at 12:33 PM UTC-7 on May 4, 2022.

creation_time

Type: TIMESTAMP
Provider name: CreationTime
Description: The date and time the specified Call Analytics job request was made. Timestamps are in the format YYYY-MM-DD’T’HH:MM:SS.SSSSSS-UTC. For example, 2022-05-04T12:32:58.761000-07:00 represents a transcription job that started processing at 12:32 PM UTC-7 on May 4, 2022.

data_access_role_arn

Type: STRING
Provider name: DataAccessRoleArn
Description: The Amazon Resource Name (ARN) you included in your request.

failure_reason

Type: STRING
Provider name: FailureReason
Description: If CallAnalyticsJobStatus is FAILED, FailureReason contains information about why the Call Analytics job request failed. The FailureReason field contains one of the following values:

• Unsupported media format. The media format specified in MediaFormat isn’t valid. Refer to refer to the MediaFormat parameter for a list of supported formats.
• The media format provided does not match the detected media format. The media format specified in MediaFormat doesn’t match the format of the input file. Check the media format of your media file and correct the specified value.
• Invalid sample rate for audio file. The sample rate specified in MediaSampleRateHertz isn’t valid. The sample rate must be between 8,000 and 48,000 hertz.
• The sample rate provided does not match the detected sample rate. The sample rate specified in MediaSampleRateHertz doesn’t match the sample rate detected in your input media file. Check the sample rate of your media file and correct the specified value.
• Invalid file size: file size too large. The size of your media file is larger than what Amazon Transcribe can process. For more information, refer to Service quotas.
• Invalid number of channels: number of channels too large. Your audio contains more channels than Amazon Transcribe is able to process. For more information, refer to Service quotas.

identified_language_score

Type: FLOAT
Provider name: IdentifiedLanguageScore
Description: The confidence score associated with the language identified in your media file. Confidence scores are values between 0 and 1; a larger value indicates a higher probability that the identified language correctly matches the language spoken in your media.

language_code

Type: STRING
Provider name: LanguageCode
Description: The language code used to create your Call Analytics job. For a list of supported languages and their associated language codes, refer to the Supported languages table. If you do not know the language spoken in your media file, you can omit this field and let Amazon Transcribe automatically identify the language of your media. To improve the accuracy of language identification, you can include several language codes and Amazon Transcribe chooses the closest match for your transcription.

media

Type: STRUCT
Provider name: Media
Description: Provides the Amazon S3 location of the media file you used in your Call Analytics request.

• media_file_uri
  Type: STRING
  Provider name: MediaFileUri
  Description: The Amazon S3 location of the media file you want to transcribe. For example:
  • s3://DOC-EXAMPLE-BUCKET/my-media-file.flac
  • s3://DOC-EXAMPLE-BUCKET/media-files/my-media-file.flac
  Note that the Amazon S3 bucket that contains your input media must be located in the same Amazon Web Services Region where you’re making your transcription request.
  
• redacted_media_file_uri
  Type: STRING
  Provider name: RedactedMediaFileUri
  Description: The Amazon S3 location of the media file you want to redact. For example:
  • s3://DOC-EXAMPLE-BUCKET/my-media-file.flac
  • s3://DOC-EXAMPLE-BUCKET/media-files/my-media-file.flac
  Note that the Amazon S3 bucket that contains your input media must be located in the same Amazon Web Services Region where you’re making your transcription request. RedactedMediaFileUri produces a redacted audio file in addition to a redacted transcript. It is only supported for Call Analytics (StartCallAnalyticsJob) transcription requests.
  

media_format

Type: STRING
Provider name: MediaFormat
Description: The format of the input media file.

media_sample_rate_hertz

Type: INT32
Provider name: MediaSampleRateHertz
Description: The sample rate, in hertz, of the audio track in your input media file.

settings

Type: STRUCT
Provider name: Settings
Description: Provides information on any additional settings that were included in your request. Additional settings include content redaction and language identification settings.

• content_redaction
  Type: STRUCT
  Provider name: ContentRedaction
  
  • pii_entity_types
    Type: UNORDERED_LIST_STRING
    Provider name: PiiEntityTypes
    Description: Specify which types of personally identifiable information (PII) you want to redact in your transcript. You can include as many types as you’d like, or you can select ALL. If you do not include PiiEntityTypes in your request, all PII is redacted.
    
  • redaction_output
    Type: STRING
    Provider name: RedactionOutput
    Description: Specify if you want only a redacted transcript, or if you want a redacted and an unredacted transcript. When you choose redacted Amazon Transcribe creates only a redacted transcript. When you choose redacted_and_unredacted Amazon Transcribe creates a redacted and an unredacted transcript (as two separate files).
    
  • redaction_type
    Type: STRING
    Provider name: RedactionType
    Description: Specify the category of information you want to redact; PII (personally identifiable information) is the only valid value. You can use PiiEntityTypes to choose which types of PII you want to redact. If you do not include PiiEntityTypes in your request, all PII is redacted.
    
• language_id_settings
  Type: STRING
  Provider name: LanguageIdSettings
  Description: If using automatic language identification in your request and you want to apply a custom language model, a custom vocabulary, or a custom vocabulary filter, include LanguageIdSettings with the relevant sub-parameters (VocabularyName, LanguageModelName, and VocabularyFilterName). LanguageIdSettings supports two to five language codes. Each language code you include can have an associated custom language model, custom vocabulary, and custom vocabulary filter. The language codes that you specify must match the languages of the associated custom language models, custom vocabularies, and custom vocabulary filters. It’s recommended that you include LanguageOptions when using LanguageIdSettings to ensure that the correct language dialect is identified. For example, if you specify a custom vocabulary that is in en-US but Amazon Transcribe determines that the language spoken in your media is en-AU, your custom vocabulary is not applied to your transcription. If you include LanguageOptions and include en-US as the only English language dialect, your custom vocabulary is applied to your transcription. If you want to include a custom language model, custom vocabulary, or custom vocabulary filter with your request but do not want to use automatic language identification, use instead the parameter with the LanguageModelName, VocabularyName, or VocabularyFilterName sub-parameters. For a list of languages supported with Call Analytics, refer to Supported languages and language-specific features.

• language_model_name
Type: STRING
Provider name: LanguageModelName
Description: The name of the custom language model you want to use when processing your Call Analytics job. Note that custom language model names are case sensitive. The language of the specified custom language model must match the language code that you specify in your transcription request. If the languages do not match, the custom language model isn’t applied. There are no errors or warnings associated with a language mismatch.

• language_options
Type: UNORDERED_LIST_STRING
Provider name: LanguageOptions
Description: You can specify two or more language codes that represent the languages you think may be present in your media. Including more than five is not recommended. If you’re unsure what languages are present, do not include this parameter. Including language options can improve the accuracy of language identification. For a list of languages supported with Call Analytics, refer to the Supported languages table. To transcribe speech in Modern Standard Arabic (ar-SA) in Amazon Web Services GovCloud (US) (US-West, us-gov-west-1), Amazon Web Services GovCloud (US) (US-East, us-gov-east-1), Canada (Calgary) ca-west-1 and Africa (Cape Town) af-south-1, your media file must be encoded at a sample rate of 16,000 Hz or higher.

• summarization
  Type: STRUCT
  Provider name: Summarization
  Description: Contains GenerateAbstractiveSummary, which is a required parameter if you want to enable Generative call summarization in your Call Analytics request.
  
  • generate_abstractive_summary
    Type: BOOLEAN
    Provider name: GenerateAbstractiveSummary
    Description: Enables Generative call summarization in your Call Analytics request Generative call summarization provides a summary of the transcript including important components discussed in the conversation. For more information, see Enabling generative call summarization.
    
• vocabulary_filter_method
Type: STRING
Provider name: VocabularyFilterMethod
Description: 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.

• vocabulary_filter_name
Type: STRING
Provider name: VocabularyFilterName
Description: The name of the custom vocabulary filter you want to include in your Call Analytics transcription request. Custom vocabulary filter names are case sensitive. Note that if you include VocabularyFilterName in your request, you must also include VocabularyFilterMethod.

• vocabulary_name
Type: STRING
Provider name: VocabularyName
Description: The name of the custom vocabulary you want to include in your Call Analytics transcription request. Custom vocabulary names are case sensitive.


start_time

Type: TIMESTAMP
Provider name: StartTime
Description: The date and time the specified Call Analytics job began processing. Timestamps are in the format YYYY-MM-DD’T’HH:MM:SS.SSSSSS-UTC. For example, 2022-05-04T12:32:58.789000-07:00 represents a transcription job that started processing at 12:32 PM UTC-7 on May 4, 2022.


tags

Type: UNORDERED_LIST_STRING


transcript

Type: STRUCT
Provider name: Transcript


• redacted_transcript_file_uri
Type: STRING
Provider name: RedactedTranscriptFileUri
Description: The Amazon S3 location of your redacted transcript. You can use this URI to access or download your transcript. If you included OutputBucketName in your transcription job request, this is the URI of that bucket. If you also included OutputKey in your request, your output is located in the path you specified in your request. If you didn’t include OutputBucketName in your transcription job request, your transcript is stored in a service-managed bucket, and RedactedTranscriptFileUri provides you with a temporary URI you can use for secure access to your transcript. Temporary URIs for service-managed Amazon S3 buckets are only valid for 15 minutes. If you get an AccesDenied error, you can get a new temporary URI by running a GetTranscriptionJob or ListTranscriptionJob request.

• transcript_file_uri
Type: STRING
Provider name: TranscriptFileUri
Description: The Amazon S3 location of your transcript. You can use this URI to access or download your transcript. If you included OutputBucketName in your transcription job request, this is the URI of that bucket. If you also included OutputKey in your request, your output is located in the path you specified in your request. If you didn’t include OutputBucketName in your transcription job request, your transcript is stored in a service-managed bucket, and TranscriptFileUri provides you with a temporary URI you can use for secure access to your transcript. Temporary URIs for service-managed Amazon S3 buckets are only valid for 15 minutes. If you get an AccesDenied error, you can get a new temporary URI by running a GetTranscriptionJob or ListTranscriptionJob request.