2021/10/29 - Amazon Transcribe Service - 4 updated api methods
Changes Transcribe and Transcribe Call Analytics now support automatic language identification along with custom vocabulary, vocabulary filter, custom language model and PII redaction.
{'CallAnalyticsJob': {'Settings': {'LanguageIdSettings': {'af-ZA | ar-AE | ar-SA | cy-GB | da-DK | de-CH | de-DE | en-AB | en-AU | en-GB | en-IE | en-IN | en-US | en-WL | es-ES | es-US | fa-IR | fr-CA | fr-FR | ga-IE | gd-GB | he-IL | hi-IN | id-ID | it-IT | ja-JP | ko-KR | ms-MY | nl-NL | pt-BR | pt-PT | ru-RU | ta-IN | te-IN | tr-TR | zh-CN | zh-TW | th-TH | en-ZA | en-NZ': {'LanguageModelName': 'string',
'VocabularyFilterName': 'string',
'VocabularyName': 'string'}}}}}
Returns information about a call analytics job. To see the status of the job, check the CallAnalyticsJobStatus field. If the status is COMPLETED , the job is finished and you can find the results at the location specified in the TranscriptFileUri field. If you enable personally identifiable information (PII) redaction, the redacted transcript appears in the RedactedTranscriptFileUri field.
See also: AWS API Documentation
Request Syntax
client.get_call_analytics_job(
CallAnalyticsJobName='string'
)
string
[REQUIRED]
The name of the analytics job you want information about. This value is case sensitive.
dict
Response Syntax
{
'CallAnalyticsJob': {
'CallAnalyticsJobName': 'string',
'CallAnalyticsJobStatus': 'QUEUED'|'IN_PROGRESS'|'FAILED'|'COMPLETED',
'LanguageCode': 'af-ZA'|'ar-AE'|'ar-SA'|'cy-GB'|'da-DK'|'de-CH'|'de-DE'|'en-AB'|'en-AU'|'en-GB'|'en-IE'|'en-IN'|'en-US'|'en-WL'|'es-ES'|'es-US'|'fa-IR'|'fr-CA'|'fr-FR'|'ga-IE'|'gd-GB'|'he-IL'|'hi-IN'|'id-ID'|'it-IT'|'ja-JP'|'ko-KR'|'ms-MY'|'nl-NL'|'pt-BR'|'pt-PT'|'ru-RU'|'ta-IN'|'te-IN'|'tr-TR'|'zh-CN'|'zh-TW'|'th-TH'|'en-ZA'|'en-NZ',
'MediaSampleRateHertz': 123,
'MediaFormat': 'mp3'|'mp4'|'wav'|'flac'|'ogg'|'amr'|'webm',
'Media': {
'MediaFileUri': 'string',
'RedactedMediaFileUri': 'string'
},
'Transcript': {
'TranscriptFileUri': 'string',
'RedactedTranscriptFileUri': 'string'
},
'StartTime': datetime(2015, 1, 1),
'CreationTime': datetime(2015, 1, 1),
'CompletionTime': datetime(2015, 1, 1),
'FailureReason': 'string',
'DataAccessRoleArn': 'string',
'IdentifiedLanguageScore': ...,
'Settings': {
'VocabularyName': 'string',
'VocabularyFilterName': 'string',
'VocabularyFilterMethod': 'remove'|'mask'|'tag',
'LanguageModelName': 'string',
'ContentRedaction': {
'RedactionType': 'PII',
'RedactionOutput': 'redacted'|'redacted_and_unredacted'
},
'LanguageOptions': [
'af-ZA'|'ar-AE'|'ar-SA'|'cy-GB'|'da-DK'|'de-CH'|'de-DE'|'en-AB'|'en-AU'|'en-GB'|'en-IE'|'en-IN'|'en-US'|'en-WL'|'es-ES'|'es-US'|'fa-IR'|'fr-CA'|'fr-FR'|'ga-IE'|'gd-GB'|'he-IL'|'hi-IN'|'id-ID'|'it-IT'|'ja-JP'|'ko-KR'|'ms-MY'|'nl-NL'|'pt-BR'|'pt-PT'|'ru-RU'|'ta-IN'|'te-IN'|'tr-TR'|'zh-CN'|'zh-TW'|'th-TH'|'en-ZA'|'en-NZ',
],
'LanguageIdSettings': {
'string': {
'VocabularyName': 'string',
'VocabularyFilterName': 'string',
'LanguageModelName': 'string'
}
}
},
'ChannelDefinitions': [
{
'ChannelId': 123,
'ParticipantRole': 'AGENT'|'CUSTOMER'
},
]
}
}
Response Structure
(dict) --
CallAnalyticsJob (dict) --
An object that contains the results of your call analytics job.
CallAnalyticsJobName (string) --
The name of the call analytics job.
CallAnalyticsJobStatus (string) --
The status of the analytics job.
LanguageCode (string) --
If you know the language spoken between the customer and the agent, specify a language code for this field.
If you don't know the language, you can leave this field blank, and Amazon Transcribe will use machine learning to automatically identify the language. To improve the accuracy of language identification, you can provide an array containing the possible language codes for the language spoken in your audio. Refer to Supported languages and language-specific features for additional information.
MediaSampleRateHertz (integer) --
The sample rate, in Hertz, of the audio.
MediaFormat (string) --
The format of the input audio file. Note: for call analytics jobs, only the following media formats are supported: MP3, MP4, WAV, FLAC, OGG, and WebM.
Media (dict) --
Describes the input media file in a transcription request.
MediaFileUri (string) --
The S3 object location of the input media file. The URI must be in the same region as the API endpoint that you are calling. The general form is:
For example:
For more information about S3 object names, see Object Keys in the Amazon S3 Developer Guide .
RedactedMediaFileUri (string) --
The S3 object location for your redacted output media file. This is only supported for call analytics jobs.
Transcript (dict) --
Identifies the location of a transcription.
TranscriptFileUri (string) --
The S3 object location of the transcript.
Use this URI to access the transcript. If you specified an S3 bucket in the OutputBucketName field when you created the job, this is the URI of that bucket. If you chose to store the transcript in Amazon Transcribe, this is a shareable URL that provides secure access to that location.
RedactedTranscriptFileUri (string) --
The S3 object location of the redacted transcript.
Use this URI to access the redacted transcript. If you specified an S3 bucket in the OutputBucketName field when you created the job, this is the URI of that bucket. If you chose to store the transcript in Amazon Transcribe, this is a shareable URL that provides secure access to that location.
StartTime (datetime) --
A timestamp that shows when the analytics job started processing.
CreationTime (datetime) --
A timestamp that shows when the analytics job was created.
CompletionTime (datetime) --
A timestamp that shows when the analytics job was completed.
FailureReason (string) --
If the AnalyticsJobStatus is FAILED , this field contains information about why the job failed.
The FailureReason field can contain one of the following values:
Unsupported media format : The media format specified in the MediaFormat field of the request isn't valid. See the description of the MediaFormat field for a list of valid values.
The media format provided does not match the detected media format : The media format of the audio file doesn't match the format specified in the MediaFormat field in the request. Check the media format of your media file and make sure the two values match.
Invalid sample rate for audio file : The sample rate specified in the MediaSampleRateHertz of the request 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 in the audio file doesn't match the sample rate specified in the MediaSampleRateHertz field in the request. Check the sample rate of your media file and make sure that the two values match.
Invalid file size: file size too large : The size of your audio file is larger than what Amazon Transcribe Medical can process. For more information, see Guidelines and Quotas in the Amazon Transcribe Medical Guide.
Invalid number of channels: number of channels too large : Your audio contains more channels than Amazon Transcribe Medical is configured to process. To request additional channels, see Amazon Transcribe Medical Endpoints and Quotas in the Amazon Web Services General Reference.
DataAccessRoleArn (string) --
The Amazon Resource Number (ARN) that you use to access the analytics job. ARNs have the format arn:partition:service:region:account-id:resource-type/resource-id .
IdentifiedLanguageScore (float) --
A value between zero and one that Amazon Transcribe assigned to the language that it identified in the source audio. This value appears only when you don't provide a single language code. Larger values indicate that Amazon Transcribe has higher confidence in the language that it identified
Settings (dict) --
Provides information about the settings used to run a transcription job.
VocabularyName (string) --
The name of a vocabulary to use when processing the call analytics job.
VocabularyFilterName (string) --
The name of the vocabulary filter to use when running a call analytics job. The filter that you specify must have the same language code as the analytics job.
VocabularyFilterMethod (string) --
Set to mask to remove filtered text from the transcript and replace it with three asterisks ("***") as placeholder text. Set to remove to remove filtered text from the transcript without using placeholder text. Set to tag to mark the word in the transcription output that matches the vocabulary filter. When you set the filter method to tag , the words matching your vocabulary filter are not masked or removed.
LanguageModelName (string) --
The structure used to describe a custom language model.
ContentRedaction (dict) --
Settings for content redaction within a transcription job.
RedactionType (string) --
Request parameter that defines the entities to be redacted. The only accepted value is PII .
RedactionOutput (string) --
The output transcript file stored in either the default S3 bucket or in a bucket you specify.
When you choose redacted Amazon Transcribe outputs only the redacted transcript.
When you choose redacted_and_unredacted Amazon Transcribe outputs both the redacted and unredacted transcripts.
LanguageOptions (list) --
When you run a call analytics job, you can specify the language spoken in the audio, or you can have Amazon Transcribe identify the language for you.
To specify a language, specify an array with one language code. If you don't know the language, you can leave this field blank and Amazon Transcribe will use machine learning to identify the language for you. To improve the ability of Amazon Transcribe to correctly identify the language, you can provide an array of the languages that can be present in the audio. Refer to Supported languages and language-specific features for additional information.
(string) --
LanguageIdSettings (dict) --
The language identification settings associated with your call analytics job. These settings include VocabularyName , VocabularyFilterName , and LanguageModelName .
(string) --
(dict) --
Language-specific settings that can be specified when language identification is enabled.
VocabularyName (string) --
The name of the vocabulary you want to use when processing your transcription job. The vocabulary you specify must have the same language code as the transcription job; if the languages don't match, the vocabulary won't be applied.
VocabularyFilterName (string) --
The name of the vocabulary filter you want to use when transcribing your audio. The filter you specify must have the same language code as the transcription job; if the languages don't match, the vocabulary filter won't be applied.
LanguageModelName (string) --
The name of the language model you want to use when transcribing your audio. The model you specify must have the same language code as the transcription job; if the languages don't match, the language model won't be applied.
ChannelDefinitions (list) --
Shows numeric values to indicate the channel assigned to the agent's audio and the channel assigned to the customer's audio.
(dict) --
For a call analytics job, an object that indicates the audio channel that belongs to the agent and the audio channel that belongs to the customer.
ChannelId (integer) --
A value that indicates the audio channel.
ParticipantRole (string) --
Indicates whether the person speaking on the audio channel is the agent or customer.
{'TranscriptionJob': {'LanguageIdSettings': {'af-ZA | ar-AE | ar-SA | cy-GB | da-DK | de-CH | de-DE | en-AB | en-AU | en-GB | en-IE | en-IN | en-US | en-WL | es-ES | es-US | fa-IR | fr-CA | fr-FR | ga-IE | gd-GB | he-IL | hi-IN | id-ID | it-IT | ja-JP | ko-KR | ms-MY | nl-NL | pt-BR | pt-PT | ru-RU | ta-IN | te-IN | tr-TR | zh-CN | zh-TW | th-TH | en-ZA | en-NZ': {'LanguageModelName': 'string',
'VocabularyFilterName': 'string',
'VocabularyName': 'string'}}}}
Returns information about a transcription job. To see the status of the job, check the TranscriptionJobStatus field. If the status is COMPLETED , the job is finished and you can find the results at the location specified in the TranscriptFileUri field. If you enable content redaction, the redacted transcript appears in RedactedTranscriptFileUri .
See also: AWS API Documentation
Request Syntax
client.get_transcription_job(
TranscriptionJobName='string'
)
string
[REQUIRED]
The name of the job.
dict
Response Syntax
{
'TranscriptionJob': {
'TranscriptionJobName': 'string',
'TranscriptionJobStatus': 'QUEUED'|'IN_PROGRESS'|'FAILED'|'COMPLETED',
'LanguageCode': 'af-ZA'|'ar-AE'|'ar-SA'|'cy-GB'|'da-DK'|'de-CH'|'de-DE'|'en-AB'|'en-AU'|'en-GB'|'en-IE'|'en-IN'|'en-US'|'en-WL'|'es-ES'|'es-US'|'fa-IR'|'fr-CA'|'fr-FR'|'ga-IE'|'gd-GB'|'he-IL'|'hi-IN'|'id-ID'|'it-IT'|'ja-JP'|'ko-KR'|'ms-MY'|'nl-NL'|'pt-BR'|'pt-PT'|'ru-RU'|'ta-IN'|'te-IN'|'tr-TR'|'zh-CN'|'zh-TW'|'th-TH'|'en-ZA'|'en-NZ',
'MediaSampleRateHertz': 123,
'MediaFormat': 'mp3'|'mp4'|'wav'|'flac'|'ogg'|'amr'|'webm',
'Media': {
'MediaFileUri': 'string',
'RedactedMediaFileUri': 'string'
},
'Transcript': {
'TranscriptFileUri': 'string',
'RedactedTranscriptFileUri': 'string'
},
'StartTime': datetime(2015, 1, 1),
'CreationTime': datetime(2015, 1, 1),
'CompletionTime': datetime(2015, 1, 1),
'FailureReason': 'string',
'Settings': {
'VocabularyName': 'string',
'ShowSpeakerLabels': True|False,
'MaxSpeakerLabels': 123,
'ChannelIdentification': True|False,
'ShowAlternatives': True|False,
'MaxAlternatives': 123,
'VocabularyFilterName': 'string',
'VocabularyFilterMethod': 'remove'|'mask'|'tag'
},
'ModelSettings': {
'LanguageModelName': 'string'
},
'JobExecutionSettings': {
'AllowDeferredExecution': True|False,
'DataAccessRoleArn': 'string'
},
'ContentRedaction': {
'RedactionType': 'PII',
'RedactionOutput': 'redacted'|'redacted_and_unredacted'
},
'IdentifyLanguage': True|False,
'LanguageOptions': [
'af-ZA'|'ar-AE'|'ar-SA'|'cy-GB'|'da-DK'|'de-CH'|'de-DE'|'en-AB'|'en-AU'|'en-GB'|'en-IE'|'en-IN'|'en-US'|'en-WL'|'es-ES'|'es-US'|'fa-IR'|'fr-CA'|'fr-FR'|'ga-IE'|'gd-GB'|'he-IL'|'hi-IN'|'id-ID'|'it-IT'|'ja-JP'|'ko-KR'|'ms-MY'|'nl-NL'|'pt-BR'|'pt-PT'|'ru-RU'|'ta-IN'|'te-IN'|'tr-TR'|'zh-CN'|'zh-TW'|'th-TH'|'en-ZA'|'en-NZ',
],
'IdentifiedLanguageScore': ...,
'Tags': [
{
'Key': 'string',
'Value': 'string'
},
],
'Subtitles': {
'Formats': [
'vtt'|'srt',
],
'SubtitleFileUris': [
'string',
]
},
'LanguageIdSettings': {
'string': {
'VocabularyName': 'string',
'VocabularyFilterName': 'string',
'LanguageModelName': 'string'
}
}
}
}
Response Structure
(dict) --
TranscriptionJob (dict) --
An object that contains the results of the transcription job.
TranscriptionJobName (string) --
The name of the transcription job.
TranscriptionJobStatus (string) --
The status of the transcription job.
LanguageCode (string) --
The language code for the input speech.
MediaSampleRateHertz (integer) --
The sample rate, in Hertz, of the audio track in the input media file.
MediaFormat (string) --
The format of the input media file.
Media (dict) --
An object that describes the input media for the transcription job.
MediaFileUri (string) --
The S3 object location of the input media file. The URI must be in the same region as the API endpoint that you are calling. The general form is:
For example:
For more information about S3 object names, see Object Keys in the Amazon S3 Developer Guide .
RedactedMediaFileUri (string) --
The S3 object location for your redacted output media file. This is only supported for call analytics jobs.
Transcript (dict) --
An object that describes the output of the transcription job.
TranscriptFileUri (string) --
The S3 object location of the transcript.
Use this URI to access the transcript. If you specified an S3 bucket in the OutputBucketName field when you created the job, this is the URI of that bucket. If you chose to store the transcript in Amazon Transcribe, this is a shareable URL that provides secure access to that location.
RedactedTranscriptFileUri (string) --
The S3 object location of the redacted transcript.
Use this URI to access the redacted transcript. If you specified an S3 bucket in the OutputBucketName field when you created the job, this is the URI of that bucket. If you chose to store the transcript in Amazon Transcribe, this is a shareable URL that provides secure access to that location.
StartTime (datetime) --
A timestamp that shows when the job started processing.
CreationTime (datetime) --
A timestamp that shows when the job was created.
CompletionTime (datetime) --
A timestamp that shows when the job completed.
FailureReason (string) --
If the TranscriptionJobStatus field is FAILED , this field contains information about why the job failed.
The FailureReason field can contain one of the following values:
Unsupported media format - The media format specified in the MediaFormat field of the request isn't valid. See the description of the MediaFormat field for a list of valid values.
The media format provided does not match the detected media format - The media format of the audio file doesn't match the format specified in the MediaFormat field in the request. Check the media format of your media file and make sure that the two values match.
Invalid sample rate for audio file - The sample rate specified in the MediaSampleRateHertz of the request 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 in the audio file doesn't match the sample rate specified in the MediaSampleRateHertz field in the request. Check the sample rate of your media file and make sure that the two values match.
Invalid file size: file size too large - The size of your audio file is larger than Amazon Transcribe can process. For more information, see Limits in the Amazon Transcribe Developer Guide .
Invalid number of channels: number of channels too large - Your audio contains more channels than Amazon Transcribe is configured to process. To request additional channels, see Amazon Transcribe Limits in the Amazon Web Services General Reference .
Settings (dict) --
Optional settings for the transcription job. Use these settings to turn on speaker recognition, to set the maximum number of speakers that should be identified and to specify a custom vocabulary to use when processing the transcription job.
VocabularyName (string) --
The name of a vocabulary to use when processing the transcription job.
ShowSpeakerLabels (boolean) --
Determines whether the transcription job uses speaker recognition to identify different speakers in the input audio. Speaker recognition labels individual speakers in the audio file. If you set the ShowSpeakerLabels field to true, you must also set the maximum number of speaker labels MaxSpeakerLabels field.
You can't set both ShowSpeakerLabels and ChannelIdentification in the same request. If you set both, your request returns a BadRequestException .
MaxSpeakerLabels (integer) --
The maximum number of speakers to identify in the input audio. If there are more speakers in the audio than this number, multiple speakers are identified as a single speaker. If you specify the MaxSpeakerLabels field, you must set the ShowSpeakerLabels field to true.
ChannelIdentification (boolean) --
Instructs Amazon Transcribe to process each audio channel separately and then merge the transcription output of each channel into a single transcription.
Amazon Transcribe also produces a transcription of each item detected on an audio channel, including the start time and end time of the item and alternative transcriptions of the item including the confidence that Amazon Transcribe has in the transcription.
You can't set both ShowSpeakerLabels and ChannelIdentification in the same request. If you set both, your request returns a BadRequestException .
ShowAlternatives (boolean) --
Determines whether the transcription contains alternative transcriptions. If you set the ShowAlternatives field to true, you must also set the maximum number of alternatives to return in the MaxAlternatives field.
MaxAlternatives (integer) --
The number of alternative transcriptions that the service should return. If you specify the MaxAlternatives field, you must set the ShowAlternatives field to true.
VocabularyFilterName (string) --
The name of the vocabulary filter to use when transcribing the audio. The filter that you specify must have the same language code as the transcription job.
VocabularyFilterMethod (string) --
Set to mask to remove filtered text from the transcript and replace it with three asterisks ("***") as placeholder text. Set to remove to remove filtered text from the transcript without using placeholder text. Set to tag to mark the word in the transcription output that matches the vocabulary filter. When you set the filter method to tag , the words matching your vocabulary filter are not masked or removed.
ModelSettings (dict) --
An object containing the details of your custom language model.
LanguageModelName (string) --
The name of your custom language model.
JobExecutionSettings (dict) --
Provides information about how a transcription job is executed.
AllowDeferredExecution (boolean) --
Indicates whether a job should be queued by Amazon Transcribe when the concurrent execution limit is exceeded. When the AllowDeferredExecution field is true, jobs are queued and executed when the number of executing jobs falls below the concurrent execution limit. If the field is false, Amazon Transcribe returns a LimitExceededException exception.
Note that job queuing is enabled by default for call analytics jobs.
If you specify the AllowDeferredExecution field, you must specify the DataAccessRoleArn field.
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN), in the form arn:partition:service:region:account-id:resource-type/resource-id , of a role that has access to the S3 bucket that contains the input files. Amazon Transcribe assumes this role to read queued media files. If you have specified an output S3 bucket for the transcription results, this role should have access to the output bucket as well.
If you specify the AllowDeferredExecution field, you must specify the DataAccessRoleArn field.
ContentRedaction (dict) --
An object that describes content redaction settings for the transcription job.
RedactionType (string) --
Request parameter that defines the entities to be redacted. The only accepted value is PII .
RedactionOutput (string) --
The output transcript file stored in either the default S3 bucket or in a bucket you specify.
When you choose redacted Amazon Transcribe outputs only the redacted transcript.
When you choose redacted_and_unredacted Amazon Transcribe outputs both the redacted and unredacted transcripts.
IdentifyLanguage (boolean) --
A value that shows if automatic language identification was enabled for a transcription job.
LanguageOptions (list) --
An object that shows the optional array of languages inputted for transcription jobs with automatic language identification enabled.
(string) --
IdentifiedLanguageScore (float) --
A value between zero and one that Amazon Transcribe assigned to the language that it identified in the source audio. Larger values indicate that Amazon Transcribe has higher confidence in the language it identified.
Tags (list) --
A key:value pair assigned to a given transcription job.
(dict) --
A key:value pair that adds metadata to a resource used by Amazon Transcribe. For example, a tag with the key:value pair ‘Department’:’Sales’ might be added to a resource to indicate its use by your organization's sales department.
Key (string) --
The first part of a key:value pair that forms a tag associated with a given resource. For example, in the tag ‘Department’:’Sales’, the key is 'Department'.
Value (string) --
The second part of a key:value pair that forms a tag associated with a given resource. For example, in the tag ‘Department’:’Sales’, the value is 'Sales'.
Subtitles (dict) --
Generate subtitles for your batch transcription job.
Formats (list) --
Specify the output format for your subtitle file; if you select both SRT and VTT formats, two output files are genereated.
(string) --
SubtitleFileUris (list) --
Choose the output location for your subtitle file. This location must be an S3 bucket.
(string) --
LanguageIdSettings (dict) --
Language-specific settings that can be specified when language identification is enabled for your transcription job. These settings include VocabularyName , VocabularyFilterName , and LanguageModelName LanguageModelName.
(string) --
(dict) --
Language-specific settings that can be specified when language identification is enabled.
VocabularyName (string) --
The name of the vocabulary you want to use when processing your transcription job. The vocabulary you specify must have the same language code as the transcription job; if the languages don't match, the vocabulary won't be applied.
VocabularyFilterName (string) --
The name of the vocabulary filter you want to use when transcribing your audio. The filter you specify must have the same language code as the transcription job; if the languages don't match, the vocabulary filter won't be applied.
LanguageModelName (string) --
The name of the language model you want to use when transcribing your audio. The model you specify must have the same language code as the transcription job; if the languages don't match, the language model won't be applied.
{'Settings': {'LanguageIdSettings': {'af-ZA | ar-AE | ar-SA | cy-GB | da-DK | de-CH | de-DE | en-AB | en-AU | en-GB | en-IE | en-IN | en-US | en-WL | es-ES | es-US | fa-IR | fr-CA | fr-FR | ga-IE | gd-GB | he-IL | hi-IN | id-ID | it-IT | ja-JP | ko-KR | ms-MY | nl-NL | pt-BR | pt-PT | ru-RU | ta-IN | te-IN | tr-TR | zh-CN | zh-TW | th-TH | en-ZA | en-NZ': {'LanguageModelName': 'string',
'VocabularyFilterName': 'string',
'VocabularyName': 'string'}}}}
Response {'CallAnalyticsJob': {'Settings': {'LanguageIdSettings': {'af-ZA | ar-AE | ar-SA | cy-GB | da-DK | de-CH | de-DE | en-AB | en-AU | en-GB | en-IE | en-IN | en-US | en-WL | es-ES | es-US | fa-IR | fr-CA | fr-FR | ga-IE | gd-GB | he-IL | hi-IN | id-ID | it-IT | ja-JP | ko-KR | ms-MY | nl-NL | pt-BR | pt-PT | ru-RU | ta-IN | te-IN | tr-TR | zh-CN | zh-TW | th-TH | en-ZA | en-NZ': {'LanguageModelName': 'string',
'VocabularyFilterName': 'string',
'VocabularyName': 'string'}}}}}
Starts an asynchronous analytics job that not only transcribes the audio recording of a caller and agent, but also returns additional insights. These insights include how quickly or loudly the caller or agent was speaking. To retrieve additional insights with your analytics jobs, create categories. A category is a way to classify analytics jobs based on attributes, such as a customer's sentiment or a particular phrase being used during the call. For more information, see the operation.
See also: AWS API Documentation
Request Syntax
client.start_call_analytics_job(
CallAnalyticsJobName='string',
Media={
'MediaFileUri': 'string',
'RedactedMediaFileUri': 'string'
},
OutputLocation='string',
OutputEncryptionKMSKeyId='string',
DataAccessRoleArn='string',
Settings={
'VocabularyName': 'string',
'VocabularyFilterName': 'string',
'VocabularyFilterMethod': 'remove'|'mask'|'tag',
'LanguageModelName': 'string',
'ContentRedaction': {
'RedactionType': 'PII',
'RedactionOutput': 'redacted'|'redacted_and_unredacted'
},
'LanguageOptions': [
'af-ZA'|'ar-AE'|'ar-SA'|'cy-GB'|'da-DK'|'de-CH'|'de-DE'|'en-AB'|'en-AU'|'en-GB'|'en-IE'|'en-IN'|'en-US'|'en-WL'|'es-ES'|'es-US'|'fa-IR'|'fr-CA'|'fr-FR'|'ga-IE'|'gd-GB'|'he-IL'|'hi-IN'|'id-ID'|'it-IT'|'ja-JP'|'ko-KR'|'ms-MY'|'nl-NL'|'pt-BR'|'pt-PT'|'ru-RU'|'ta-IN'|'te-IN'|'tr-TR'|'zh-CN'|'zh-TW'|'th-TH'|'en-ZA'|'en-NZ',
],
'LanguageIdSettings': {
'string': {
'VocabularyName': 'string',
'VocabularyFilterName': 'string',
'LanguageModelName': 'string'
}
}
},
ChannelDefinitions=[
{
'ChannelId': 123,
'ParticipantRole': 'AGENT'|'CUSTOMER'
},
]
)
string
[REQUIRED]
The name of the call analytics job. You can't use the string "." or ".." by themselves as the job name. The name must also be unique within an Amazon Web Services account. If you try to create a call analytics job with the same name as a previous call analytics job, you get a ConflictException error.
dict
[REQUIRED]
Describes the input media file in a transcription request.
MediaFileUri (string) --
The S3 object location of the input media file. The URI must be in the same region as the API endpoint that you are calling. The general form is:
For example:
For more information about S3 object names, see Object Keys in the Amazon S3 Developer Guide .
RedactedMediaFileUri (string) --
The S3 object location for your redacted output media file. This is only supported for call analytics jobs.
string
The Amazon S3 location where the output of the call analytics job is stored. You can provide the following location types to store the output of call analytics job:
s3://DOC-EXAMPLE-BUCKET1 If you specify a bucket, Amazon Transcribe saves the output of the analytics job as a JSON file at the root level of the bucket.
s3://DOC-EXAMPLE-BUCKET1/folder/ f you specify a path, Amazon Transcribe saves the output of the analytics job as s3://DOC-EXAMPLE-BUCKET1/folder/your-transcription-job-name.json If you specify a folder, you must provide a trailing slash.
s3://DOC-EXAMPLE-BUCKET1/folder/filename.json If you provide a path that has the filename specified, Amazon Transcribe saves the output of the analytics job as s3://DOC-EXAMPLEBUCKET1/folder/filename.json
You can specify an Amazon Web Services Key Management Service (KMS) key to encrypt the output of our analytics job using the OutputEncryptionKMSKeyId parameter. If you don't specify a KMS key, Amazon Transcribe uses the default Amazon S3 key for server-side encryption of the analytics job output that is placed in your S3 bucket.
string
The Amazon Resource Name (ARN) of the Amazon Web Services Key Management Service key used to encrypt the output of the call analytics job. The user calling the operation must have permission to use the specified KMS key.
You use either of the following to identify an Amazon Web Services KMS key in the current account:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
KMS Key Alias: "alias/ExampleAlias"
You can use either of the following to identify a KMS key in the current account or another account:
Amazon Resource Name (ARN) of a KMS key in the current account or another account: "arn:aws:kms:region:account ID:key/1234abcd-12ab-34cd-56ef1234567890ab"
ARN of a KMS Key Alias: "arn:aws:kms:region:account ID:alias/ExampleAlias"
If you don't specify an encryption key, the output of the call analytics job is encrypted with the default Amazon S3 key (SSE-S3).
If you specify a KMS key to encrypt your output, you must also specify an output location in the OutputLocation parameter.
string
[REQUIRED]
The Amazon Resource Name (ARN) of a role that has access to the S3 bucket that contains your input files. Amazon Transcribe assumes this role to read queued audio files. If you have specified an output S3 bucket for your transcription results, this role should have access to the output bucket as well.
dict
A Settings object that provides optional settings for a call analytics job.
VocabularyName (string) --
The name of a vocabulary to use when processing the call analytics job.
VocabularyFilterName (string) --
The name of the vocabulary filter to use when running a call analytics job. The filter that you specify must have the same language code as the analytics job.
VocabularyFilterMethod (string) --
Set to mask to remove filtered text from the transcript and replace it with three asterisks ("***") as placeholder text. Set to remove to remove filtered text from the transcript without using placeholder text. Set to tag to mark the word in the transcription output that matches the vocabulary filter. When you set the filter method to tag , the words matching your vocabulary filter are not masked or removed.
LanguageModelName (string) --
The structure used to describe a custom language model.
ContentRedaction (dict) --
Settings for content redaction within a transcription job.
RedactionType (string) -- [REQUIRED]
Request parameter that defines the entities to be redacted. The only accepted value is PII .
RedactionOutput (string) -- [REQUIRED]
The output transcript file stored in either the default S3 bucket or in a bucket you specify.
When you choose redacted Amazon Transcribe outputs only the redacted transcript.
When you choose redacted_and_unredacted Amazon Transcribe outputs both the redacted and unredacted transcripts.
LanguageOptions (list) --
When you run a call analytics job, you can specify the language spoken in the audio, or you can have Amazon Transcribe identify the language for you.
To specify a language, specify an array with one language code. If you don't know the language, you can leave this field blank and Amazon Transcribe will use machine learning to identify the language for you. To improve the ability of Amazon Transcribe to correctly identify the language, you can provide an array of the languages that can be present in the audio. Refer to Supported languages and language-specific features for additional information.
(string) --
LanguageIdSettings (dict) --
The language identification settings associated with your call analytics job. These settings include VocabularyName , VocabularyFilterName , and LanguageModelName .
(string) --
(dict) --
Language-specific settings that can be specified when language identification is enabled.
VocabularyName (string) --
The name of the vocabulary you want to use when processing your transcription job. The vocabulary you specify must have the same language code as the transcription job; if the languages don't match, the vocabulary won't be applied.
VocabularyFilterName (string) --
The name of the vocabulary filter you want to use when transcribing your audio. The filter you specify must have the same language code as the transcription job; if the languages don't match, the vocabulary filter won't be applied.
LanguageModelName (string) --
The name of the language model you want to use when transcribing your audio. The model you specify must have the same language code as the transcription job; if the languages don't match, the language model won't be applied.
list
When you start a call analytics job, you must pass an array that maps the agent and the customer to specific audio channels. The values you can assign to a channel are 0 and 1. The agent and the customer must each have their own channel. You can't assign more than one channel to an agent or customer.
(dict) --
For a call analytics job, an object that indicates the audio channel that belongs to the agent and the audio channel that belongs to the customer.
ChannelId (integer) --
A value that indicates the audio channel.
ParticipantRole (string) --
Indicates whether the person speaking on the audio channel is the agent or customer.
dict
Response Syntax
{
'CallAnalyticsJob': {
'CallAnalyticsJobName': 'string',
'CallAnalyticsJobStatus': 'QUEUED'|'IN_PROGRESS'|'FAILED'|'COMPLETED',
'LanguageCode': 'af-ZA'|'ar-AE'|'ar-SA'|'cy-GB'|'da-DK'|'de-CH'|'de-DE'|'en-AB'|'en-AU'|'en-GB'|'en-IE'|'en-IN'|'en-US'|'en-WL'|'es-ES'|'es-US'|'fa-IR'|'fr-CA'|'fr-FR'|'ga-IE'|'gd-GB'|'he-IL'|'hi-IN'|'id-ID'|'it-IT'|'ja-JP'|'ko-KR'|'ms-MY'|'nl-NL'|'pt-BR'|'pt-PT'|'ru-RU'|'ta-IN'|'te-IN'|'tr-TR'|'zh-CN'|'zh-TW'|'th-TH'|'en-ZA'|'en-NZ',
'MediaSampleRateHertz': 123,
'MediaFormat': 'mp3'|'mp4'|'wav'|'flac'|'ogg'|'amr'|'webm',
'Media': {
'MediaFileUri': 'string',
'RedactedMediaFileUri': 'string'
},
'Transcript': {
'TranscriptFileUri': 'string',
'RedactedTranscriptFileUri': 'string'
},
'StartTime': datetime(2015, 1, 1),
'CreationTime': datetime(2015, 1, 1),
'CompletionTime': datetime(2015, 1, 1),
'FailureReason': 'string',
'DataAccessRoleArn': 'string',
'IdentifiedLanguageScore': ...,
'Settings': {
'VocabularyName': 'string',
'VocabularyFilterName': 'string',
'VocabularyFilterMethod': 'remove'|'mask'|'tag',
'LanguageModelName': 'string',
'ContentRedaction': {
'RedactionType': 'PII',
'RedactionOutput': 'redacted'|'redacted_and_unredacted'
},
'LanguageOptions': [
'af-ZA'|'ar-AE'|'ar-SA'|'cy-GB'|'da-DK'|'de-CH'|'de-DE'|'en-AB'|'en-AU'|'en-GB'|'en-IE'|'en-IN'|'en-US'|'en-WL'|'es-ES'|'es-US'|'fa-IR'|'fr-CA'|'fr-FR'|'ga-IE'|'gd-GB'|'he-IL'|'hi-IN'|'id-ID'|'it-IT'|'ja-JP'|'ko-KR'|'ms-MY'|'nl-NL'|'pt-BR'|'pt-PT'|'ru-RU'|'ta-IN'|'te-IN'|'tr-TR'|'zh-CN'|'zh-TW'|'th-TH'|'en-ZA'|'en-NZ',
],
'LanguageIdSettings': {
'string': {
'VocabularyName': 'string',
'VocabularyFilterName': 'string',
'LanguageModelName': 'string'
}
}
},
'ChannelDefinitions': [
{
'ChannelId': 123,
'ParticipantRole': 'AGENT'|'CUSTOMER'
},
]
}
}
Response Structure
(dict) --
CallAnalyticsJob (dict) --
An object containing the details of the asynchronous call analytics job.
CallAnalyticsJobName (string) --
The name of the call analytics job.
CallAnalyticsJobStatus (string) --
The status of the analytics job.
LanguageCode (string) --
If you know the language spoken between the customer and the agent, specify a language code for this field.
If you don't know the language, you can leave this field blank, and Amazon Transcribe will use machine learning to automatically identify the language. To improve the accuracy of language identification, you can provide an array containing the possible language codes for the language spoken in your audio. Refer to Supported languages and language-specific features for additional information.
MediaSampleRateHertz (integer) --
The sample rate, in Hertz, of the audio.
MediaFormat (string) --
The format of the input audio file. Note: for call analytics jobs, only the following media formats are supported: MP3, MP4, WAV, FLAC, OGG, and WebM.
Media (dict) --
Describes the input media file in a transcription request.
MediaFileUri (string) --
The S3 object location of the input media file. The URI must be in the same region as the API endpoint that you are calling. The general form is:
For example:
For more information about S3 object names, see Object Keys in the Amazon S3 Developer Guide .
RedactedMediaFileUri (string) --
The S3 object location for your redacted output media file. This is only supported for call analytics jobs.
Transcript (dict) --
Identifies the location of a transcription.
TranscriptFileUri (string) --
The S3 object location of the transcript.
Use this URI to access the transcript. If you specified an S3 bucket in the OutputBucketName field when you created the job, this is the URI of that bucket. If you chose to store the transcript in Amazon Transcribe, this is a shareable URL that provides secure access to that location.
RedactedTranscriptFileUri (string) --
The S3 object location of the redacted transcript.
Use this URI to access the redacted transcript. If you specified an S3 bucket in the OutputBucketName field when you created the job, this is the URI of that bucket. If you chose to store the transcript in Amazon Transcribe, this is a shareable URL that provides secure access to that location.
StartTime (datetime) --
A timestamp that shows when the analytics job started processing.
CreationTime (datetime) --
A timestamp that shows when the analytics job was created.
CompletionTime (datetime) --
A timestamp that shows when the analytics job was completed.
FailureReason (string) --
If the AnalyticsJobStatus is FAILED , this field contains information about why the job failed.
The FailureReason field can contain one of the following values:
Unsupported media format : The media format specified in the MediaFormat field of the request isn't valid. See the description of the MediaFormat field for a list of valid values.
The media format provided does not match the detected media format : The media format of the audio file doesn't match the format specified in the MediaFormat field in the request. Check the media format of your media file and make sure the two values match.
Invalid sample rate for audio file : The sample rate specified in the MediaSampleRateHertz of the request 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 in the audio file doesn't match the sample rate specified in the MediaSampleRateHertz field in the request. Check the sample rate of your media file and make sure that the two values match.
Invalid file size: file size too large : The size of your audio file is larger than what Amazon Transcribe Medical can process. For more information, see Guidelines and Quotas in the Amazon Transcribe Medical Guide.
Invalid number of channels: number of channels too large : Your audio contains more channels than Amazon Transcribe Medical is configured to process. To request additional channels, see Amazon Transcribe Medical Endpoints and Quotas in the Amazon Web Services General Reference.
DataAccessRoleArn (string) --
The Amazon Resource Number (ARN) that you use to access the analytics job. ARNs have the format arn:partition:service:region:account-id:resource-type/resource-id .
IdentifiedLanguageScore (float) --
A value between zero and one that Amazon Transcribe assigned to the language that it identified in the source audio. This value appears only when you don't provide a single language code. Larger values indicate that Amazon Transcribe has higher confidence in the language that it identified
Settings (dict) --
Provides information about the settings used to run a transcription job.
VocabularyName (string) --
The name of a vocabulary to use when processing the call analytics job.
VocabularyFilterName (string) --
The name of the vocabulary filter to use when running a call analytics job. The filter that you specify must have the same language code as the analytics job.
VocabularyFilterMethod (string) --
Set to mask to remove filtered text from the transcript and replace it with three asterisks ("***") as placeholder text. Set to remove to remove filtered text from the transcript without using placeholder text. Set to tag to mark the word in the transcription output that matches the vocabulary filter. When you set the filter method to tag , the words matching your vocabulary filter are not masked or removed.
LanguageModelName (string) --
The structure used to describe a custom language model.
ContentRedaction (dict) --
Settings for content redaction within a transcription job.
RedactionType (string) --
Request parameter that defines the entities to be redacted. The only accepted value is PII .
RedactionOutput (string) --
The output transcript file stored in either the default S3 bucket or in a bucket you specify.
When you choose redacted Amazon Transcribe outputs only the redacted transcript.
When you choose redacted_and_unredacted Amazon Transcribe outputs both the redacted and unredacted transcripts.
LanguageOptions (list) --
When you run a call analytics job, you can specify the language spoken in the audio, or you can have Amazon Transcribe identify the language for you.
To specify a language, specify an array with one language code. If you don't know the language, you can leave this field blank and Amazon Transcribe will use machine learning to identify the language for you. To improve the ability of Amazon Transcribe to correctly identify the language, you can provide an array of the languages that can be present in the audio. Refer to Supported languages and language-specific features for additional information.
(string) --
LanguageIdSettings (dict) --
The language identification settings associated with your call analytics job. These settings include VocabularyName , VocabularyFilterName , and LanguageModelName .
(string) --
(dict) --
Language-specific settings that can be specified when language identification is enabled.
VocabularyName (string) --
The name of the vocabulary you want to use when processing your transcription job. The vocabulary you specify must have the same language code as the transcription job; if the languages don't match, the vocabulary won't be applied.
VocabularyFilterName (string) --
The name of the vocabulary filter you want to use when transcribing your audio. The filter you specify must have the same language code as the transcription job; if the languages don't match, the vocabulary filter won't be applied.
LanguageModelName (string) --
The name of the language model you want to use when transcribing your audio. The model you specify must have the same language code as the transcription job; if the languages don't match, the language model won't be applied.
ChannelDefinitions (list) --
Shows numeric values to indicate the channel assigned to the agent's audio and the channel assigned to the customer's audio.
(dict) --
For a call analytics job, an object that indicates the audio channel that belongs to the agent and the audio channel that belongs to the customer.
ChannelId (integer) --
A value that indicates the audio channel.
ParticipantRole (string) --
Indicates whether the person speaking on the audio channel is the agent or customer.
{'LanguageIdSettings': {'af-ZA | ar-AE | ar-SA | cy-GB | da-DK | de-CH | de-DE | en-AB | en-AU | en-GB | en-IE | en-IN | en-US | en-WL | es-ES | es-US | fa-IR | fr-CA | fr-FR | ga-IE | gd-GB | he-IL | hi-IN | id-ID | it-IT | ja-JP | ko-KR | ms-MY | nl-NL | pt-BR | pt-PT | ru-RU | ta-IN | te-IN | tr-TR | zh-CN | zh-TW | th-TH | en-ZA | en-NZ': {'LanguageModelName': 'string',
'VocabularyFilterName': 'string',
'VocabularyName': 'string'}}}
Response {'TranscriptionJob': {'LanguageIdSettings': {'af-ZA | ar-AE | ar-SA | cy-GB | da-DK | de-CH | de-DE | en-AB | en-AU | en-GB | en-IE | en-IN | en-US | en-WL | es-ES | es-US | fa-IR | fr-CA | fr-FR | ga-IE | gd-GB | he-IL | hi-IN | id-ID | it-IT | ja-JP | ko-KR | ms-MY | nl-NL | pt-BR | pt-PT | ru-RU | ta-IN | te-IN | tr-TR | zh-CN | zh-TW | th-TH | en-ZA | en-NZ': {'LanguageModelName': 'string',
'VocabularyFilterName': 'string',
'VocabularyName': 'string'}}}}
Starts an asynchronous job to transcribe speech to text.
See also: AWS API Documentation
Request Syntax
client.start_transcription_job(
TranscriptionJobName='string',
LanguageCode='af-ZA'|'ar-AE'|'ar-SA'|'cy-GB'|'da-DK'|'de-CH'|'de-DE'|'en-AB'|'en-AU'|'en-GB'|'en-IE'|'en-IN'|'en-US'|'en-WL'|'es-ES'|'es-US'|'fa-IR'|'fr-CA'|'fr-FR'|'ga-IE'|'gd-GB'|'he-IL'|'hi-IN'|'id-ID'|'it-IT'|'ja-JP'|'ko-KR'|'ms-MY'|'nl-NL'|'pt-BR'|'pt-PT'|'ru-RU'|'ta-IN'|'te-IN'|'tr-TR'|'zh-CN'|'zh-TW'|'th-TH'|'en-ZA'|'en-NZ',
MediaSampleRateHertz=123,
MediaFormat='mp3'|'mp4'|'wav'|'flac'|'ogg'|'amr'|'webm',
Media={
'MediaFileUri': 'string',
'RedactedMediaFileUri': 'string'
},
OutputBucketName='string',
OutputKey='string',
OutputEncryptionKMSKeyId='string',
KMSEncryptionContext={
'string': 'string'
},
Settings={
'VocabularyName': 'string',
'ShowSpeakerLabels': True|False,
'MaxSpeakerLabels': 123,
'ChannelIdentification': True|False,
'ShowAlternatives': True|False,
'MaxAlternatives': 123,
'VocabularyFilterName': 'string',
'VocabularyFilterMethod': 'remove'|'mask'|'tag'
},
ModelSettings={
'LanguageModelName': 'string'
},
JobExecutionSettings={
'AllowDeferredExecution': True|False,
'DataAccessRoleArn': 'string'
},
ContentRedaction={
'RedactionType': 'PII',
'RedactionOutput': 'redacted'|'redacted_and_unredacted'
},
IdentifyLanguage=True|False,
LanguageOptions=[
'af-ZA'|'ar-AE'|'ar-SA'|'cy-GB'|'da-DK'|'de-CH'|'de-DE'|'en-AB'|'en-AU'|'en-GB'|'en-IE'|'en-IN'|'en-US'|'en-WL'|'es-ES'|'es-US'|'fa-IR'|'fr-CA'|'fr-FR'|'ga-IE'|'gd-GB'|'he-IL'|'hi-IN'|'id-ID'|'it-IT'|'ja-JP'|'ko-KR'|'ms-MY'|'nl-NL'|'pt-BR'|'pt-PT'|'ru-RU'|'ta-IN'|'te-IN'|'tr-TR'|'zh-CN'|'zh-TW'|'th-TH'|'en-ZA'|'en-NZ',
],
Subtitles={
'Formats': [
'vtt'|'srt',
]
},
Tags=[
{
'Key': 'string',
'Value': 'string'
},
],
LanguageIdSettings={
'string': {
'VocabularyName': 'string',
'VocabularyFilterName': 'string',
'LanguageModelName': 'string'
}
}
)
string
[REQUIRED]
The name of the job. You can't use the strings " . " or " .. " by themselves as the job name. The name must also be unique within an Amazon Web Services account. If you try to create a transcription job with the same name as a previous transcription job, you get a ConflictException error.
string
The language code for the language used in the input media file.
To transcribe speech in Modern Standard Arabic (ar-SA), your audio or video file must be encoded at a sample rate of 16,000 Hz or higher.
integer
The sample rate, in Hertz, of the audio track in the input media file.
If you do not specify the media sample rate, Amazon Transcribe determines the sample rate. If you specify the sample rate, it must match the sample rate detected by Amazon Transcribe. In most cases, you should leave the MediaSampleRateHertz field blank and let Amazon Transcribe determine the sample rate.
string
The format of the input media file.
dict
[REQUIRED]
An object that describes the input media for a transcription job.
MediaFileUri (string) --
The S3 object location of the input media file. The URI must be in the same region as the API endpoint that you are calling. The general form is:
For example:
For more information about S3 object names, see Object Keys in the Amazon S3 Developer Guide .
RedactedMediaFileUri (string) --
The S3 object location for your redacted output media file. This is only supported for call analytics jobs.
string
The location where the transcription is stored.
If you set the OutputBucketName , Amazon Transcribe puts the transcript in the specified S3 bucket. When you call the GetTranscriptionJob operation, the operation returns this location in the TranscriptFileUri field. If you enable content redaction, the redacted transcript appears in RedactedTranscriptFileUri . If you enable content redaction and choose to output an unredacted transcript, that transcript's location still appears in the TranscriptFileUri . The S3 bucket must have permissions that allow Amazon Transcribe to put files in the bucket. For more information, see Permissions Required for IAM User Roles.
You can specify an Amazon Web Services Key Management Service (KMS) key to encrypt the output of your transcription using the OutputEncryptionKMSKeyId parameter. If you don't specify a KMS key, Amazon Transcribe uses the default Amazon S3 key for server-side encryption of transcripts that are placed in your S3 bucket.
If you don't set the OutputBucketName , Amazon Transcribe generates a pre-signed URL, a shareable URL that provides secure access to your transcription, and returns it in the TranscriptFileUri field. Use this URL to download the transcription.
string
You can specify a location in an Amazon S3 bucket to store the output of your transcription job.
If you don't specify an output key, Amazon Transcribe stores the output of your transcription job in the Amazon S3 bucket you specified. By default, the object key is "your-transcription-job-name.json".
You can use output keys to specify the Amazon S3 prefix and file name of the transcription output. For example, specifying the Amazon S3 prefix, "folder1/folder2/", as an output key would lead to the output being stored as "folder1/folder2/your-transcription-job-name.json". If you specify "my-other-job-name.json" as the output key, the object key is changed to "my-other-job-name.json". You can use an output key to change both the prefix and the file name, for example "folder/my-other-job-name.json".
If you specify an output key, you must also specify an S3 bucket in the OutputBucketName parameter.
string
The Amazon Resource Name (ARN) of the Amazon Web Services Key Management Service (KMS) key used to encrypt the output of the transcription job. The user calling the StartTranscriptionJob operation must have permission to use the specified KMS key.
You can use either of the following to identify a KMS key in the current account:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
KMS Key Alias: "alias/ExampleAlias"
You can use either of the following to identify a KMS key in the current account or another account:
Amazon Resource Name (ARN) of a KMS Key: "arn:aws:kms:region:account ID:key/1234abcd-12ab-34cd-56ef-1234567890ab"
ARN of a KMS Key Alias: "arn:aws:kms:region:account-ID:alias/ExampleAlias"
If you don't specify an encryption key, the output of the transcription job is encrypted with the default Amazon S3 key (SSE-S3).
If you specify a KMS key to encrypt your output, you must also specify an output location in the OutputBucketName parameter.
dict
A map of plain text, non-secret key:value pairs, known as encryption context pairs, that provide an added layer of security for your data.
(string) --
(string) --
dict
A Settings object that provides optional settings for a transcription job.
VocabularyName (string) --
The name of a vocabulary to use when processing the transcription job.
ShowSpeakerLabels (boolean) --
Determines whether the transcription job uses speaker recognition to identify different speakers in the input audio. Speaker recognition labels individual speakers in the audio file. If you set the ShowSpeakerLabels field to true, you must also set the maximum number of speaker labels MaxSpeakerLabels field.
You can't set both ShowSpeakerLabels and ChannelIdentification in the same request. If you set both, your request returns a BadRequestException .
MaxSpeakerLabels (integer) --
The maximum number of speakers to identify in the input audio. If there are more speakers in the audio than this number, multiple speakers are identified as a single speaker. If you specify the MaxSpeakerLabels field, you must set the ShowSpeakerLabels field to true.
ChannelIdentification (boolean) --
Instructs Amazon Transcribe to process each audio channel separately and then merge the transcription output of each channel into a single transcription.
Amazon Transcribe also produces a transcription of each item detected on an audio channel, including the start time and end time of the item and alternative transcriptions of the item including the confidence that Amazon Transcribe has in the transcription.
You can't set both ShowSpeakerLabels and ChannelIdentification in the same request. If you set both, your request returns a BadRequestException .
ShowAlternatives (boolean) --
Determines whether the transcription contains alternative transcriptions. If you set the ShowAlternatives field to true, you must also set the maximum number of alternatives to return in the MaxAlternatives field.
MaxAlternatives (integer) --
The number of alternative transcriptions that the service should return. If you specify the MaxAlternatives field, you must set the ShowAlternatives field to true.
VocabularyFilterName (string) --
The name of the vocabulary filter to use when transcribing the audio. The filter that you specify must have the same language code as the transcription job.
VocabularyFilterMethod (string) --
Set to mask to remove filtered text from the transcript and replace it with three asterisks ("***") as placeholder text. Set to remove to remove filtered text from the transcript without using placeholder text. Set to tag to mark the word in the transcription output that matches the vocabulary filter. When you set the filter method to tag , the words matching your vocabulary filter are not masked or removed.
dict
Choose the custom language model you use for your transcription job in this parameter.
LanguageModelName (string) --
The name of your custom language model.
dict
Provides information about how a transcription job is executed. Use this field to indicate that the job can be queued for deferred execution if the concurrency limit is reached and there are no slots available to immediately run the job.
AllowDeferredExecution (boolean) --
Indicates whether a job should be queued by Amazon Transcribe when the concurrent execution limit is exceeded. When the AllowDeferredExecution field is true, jobs are queued and executed when the number of executing jobs falls below the concurrent execution limit. If the field is false, Amazon Transcribe returns a LimitExceededException exception.
Note that job queuing is enabled by default for call analytics jobs.
If you specify the AllowDeferredExecution field, you must specify the DataAccessRoleArn field.
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN), in the form arn:partition:service:region:account-id:resource-type/resource-id , of a role that has access to the S3 bucket that contains the input files. Amazon Transcribe assumes this role to read queued media files. If you have specified an output S3 bucket for the transcription results, this role should have access to the output bucket as well.
If you specify the AllowDeferredExecution field, you must specify the DataAccessRoleArn field.
dict
An object that contains the request parameters for content redaction.
RedactionType (string) -- [REQUIRED]
Request parameter that defines the entities to be redacted. The only accepted value is PII .
RedactionOutput (string) -- [REQUIRED]
The output transcript file stored in either the default S3 bucket or in a bucket you specify.
When you choose redacted Amazon Transcribe outputs only the redacted transcript.
When you choose redacted_and_unredacted Amazon Transcribe outputs both the redacted and unredacted transcripts.
boolean
Set this field to true to enable automatic language identification. Automatic language identification is disabled by default. You receive a BadRequestException error if you enter a value for a LanguageCode .
list
An object containing a list of languages that might be present in your collection of audio files. Automatic language identification chooses a language that best matches the source audio from that list.
To transcribe speech in Modern Standard Arabic (ar-SA), your audio or video file must be encoded at a sample rate of 16,000 Hz or higher.
(string) --
dict
Add subtitles to your batch transcription job.
Formats (list) --
Specify the output format for your subtitle file.
(string) --
list
Add tags to an Amazon Transcribe transcription job.
(dict) --
A key:value pair that adds metadata to a resource used by Amazon Transcribe. For example, a tag with the key:value pair ‘Department’:’Sales’ might be added to a resource to indicate its use by your organization's sales department.
Key (string) -- [REQUIRED]
The first part of a key:value pair that forms a tag associated with a given resource. For example, in the tag ‘Department’:’Sales’, the key is 'Department'.
Value (string) -- [REQUIRED]
The second part of a key:value pair that forms a tag associated with a given resource. For example, in the tag ‘Department’:’Sales’, the value is 'Sales'.
dict
The language identification settings associated with your transcription job. These settings include VocabularyName , VocabularyFilterName , and LanguageModelName .
(string) --
(dict) --
Language-specific settings that can be specified when language identification is enabled.
VocabularyName (string) --
The name of the vocabulary you want to use when processing your transcription job. The vocabulary you specify must have the same language code as the transcription job; if the languages don't match, the vocabulary won't be applied.
VocabularyFilterName (string) --
The name of the vocabulary filter you want to use when transcribing your audio. The filter you specify must have the same language code as the transcription job; if the languages don't match, the vocabulary filter won't be applied.
LanguageModelName (string) --
The name of the language model you want to use when transcribing your audio. The model you specify must have the same language code as the transcription job; if the languages don't match, the language model won't be applied.
dict
Response Syntax
{
'TranscriptionJob': {
'TranscriptionJobName': 'string',
'TranscriptionJobStatus': 'QUEUED'|'IN_PROGRESS'|'FAILED'|'COMPLETED',
'LanguageCode': 'af-ZA'|'ar-AE'|'ar-SA'|'cy-GB'|'da-DK'|'de-CH'|'de-DE'|'en-AB'|'en-AU'|'en-GB'|'en-IE'|'en-IN'|'en-US'|'en-WL'|'es-ES'|'es-US'|'fa-IR'|'fr-CA'|'fr-FR'|'ga-IE'|'gd-GB'|'he-IL'|'hi-IN'|'id-ID'|'it-IT'|'ja-JP'|'ko-KR'|'ms-MY'|'nl-NL'|'pt-BR'|'pt-PT'|'ru-RU'|'ta-IN'|'te-IN'|'tr-TR'|'zh-CN'|'zh-TW'|'th-TH'|'en-ZA'|'en-NZ',
'MediaSampleRateHertz': 123,
'MediaFormat': 'mp3'|'mp4'|'wav'|'flac'|'ogg'|'amr'|'webm',
'Media': {
'MediaFileUri': 'string',
'RedactedMediaFileUri': 'string'
},
'Transcript': {
'TranscriptFileUri': 'string',
'RedactedTranscriptFileUri': 'string'
},
'StartTime': datetime(2015, 1, 1),
'CreationTime': datetime(2015, 1, 1),
'CompletionTime': datetime(2015, 1, 1),
'FailureReason': 'string',
'Settings': {
'VocabularyName': 'string',
'ShowSpeakerLabels': True|False,
'MaxSpeakerLabels': 123,
'ChannelIdentification': True|False,
'ShowAlternatives': True|False,
'MaxAlternatives': 123,
'VocabularyFilterName': 'string',
'VocabularyFilterMethod': 'remove'|'mask'|'tag'
},
'ModelSettings': {
'LanguageModelName': 'string'
},
'JobExecutionSettings': {
'AllowDeferredExecution': True|False,
'DataAccessRoleArn': 'string'
},
'ContentRedaction': {
'RedactionType': 'PII',
'RedactionOutput': 'redacted'|'redacted_and_unredacted'
},
'IdentifyLanguage': True|False,
'LanguageOptions': [
'af-ZA'|'ar-AE'|'ar-SA'|'cy-GB'|'da-DK'|'de-CH'|'de-DE'|'en-AB'|'en-AU'|'en-GB'|'en-IE'|'en-IN'|'en-US'|'en-WL'|'es-ES'|'es-US'|'fa-IR'|'fr-CA'|'fr-FR'|'ga-IE'|'gd-GB'|'he-IL'|'hi-IN'|'id-ID'|'it-IT'|'ja-JP'|'ko-KR'|'ms-MY'|'nl-NL'|'pt-BR'|'pt-PT'|'ru-RU'|'ta-IN'|'te-IN'|'tr-TR'|'zh-CN'|'zh-TW'|'th-TH'|'en-ZA'|'en-NZ',
],
'IdentifiedLanguageScore': ...,
'Tags': [
{
'Key': 'string',
'Value': 'string'
},
],
'Subtitles': {
'Formats': [
'vtt'|'srt',
],
'SubtitleFileUris': [
'string',
]
},
'LanguageIdSettings': {
'string': {
'VocabularyName': 'string',
'VocabularyFilterName': 'string',
'LanguageModelName': 'string'
}
}
}
}
Response Structure
(dict) --
TranscriptionJob (dict) --
An object containing details of the asynchronous transcription job.
TranscriptionJobName (string) --
The name of the transcription job.
TranscriptionJobStatus (string) --
The status of the transcription job.
LanguageCode (string) --
The language code for the input speech.
MediaSampleRateHertz (integer) --
The sample rate, in Hertz, of the audio track in the input media file.
MediaFormat (string) --
The format of the input media file.
Media (dict) --
An object that describes the input media for the transcription job.
MediaFileUri (string) --
The S3 object location of the input media file. The URI must be in the same region as the API endpoint that you are calling. The general form is:
For example:
For more information about S3 object names, see Object Keys in the Amazon S3 Developer Guide .
RedactedMediaFileUri (string) --
The S3 object location for your redacted output media file. This is only supported for call analytics jobs.
Transcript (dict) --
An object that describes the output of the transcription job.
TranscriptFileUri (string) --
The S3 object location of the transcript.
Use this URI to access the transcript. If you specified an S3 bucket in the OutputBucketName field when you created the job, this is the URI of that bucket. If you chose to store the transcript in Amazon Transcribe, this is a shareable URL that provides secure access to that location.
RedactedTranscriptFileUri (string) --
The S3 object location of the redacted transcript.
Use this URI to access the redacted transcript. If you specified an S3 bucket in the OutputBucketName field when you created the job, this is the URI of that bucket. If you chose to store the transcript in Amazon Transcribe, this is a shareable URL that provides secure access to that location.
StartTime (datetime) --
A timestamp that shows when the job started processing.
CreationTime (datetime) --
A timestamp that shows when the job was created.
CompletionTime (datetime) --
A timestamp that shows when the job completed.
FailureReason (string) --
If the TranscriptionJobStatus field is FAILED , this field contains information about why the job failed.
The FailureReason field can contain one of the following values:
Unsupported media format - The media format specified in the MediaFormat field of the request isn't valid. See the description of the MediaFormat field for a list of valid values.
The media format provided does not match the detected media format - The media format of the audio file doesn't match the format specified in the MediaFormat field in the request. Check the media format of your media file and make sure that the two values match.
Invalid sample rate for audio file - The sample rate specified in the MediaSampleRateHertz of the request 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 in the audio file doesn't match the sample rate specified in the MediaSampleRateHertz field in the request. Check the sample rate of your media file and make sure that the two values match.
Invalid file size: file size too large - The size of your audio file is larger than Amazon Transcribe can process. For more information, see Limits in the Amazon Transcribe Developer Guide .
Invalid number of channels: number of channels too large - Your audio contains more channels than Amazon Transcribe is configured to process. To request additional channels, see Amazon Transcribe Limits in the Amazon Web Services General Reference .
Settings (dict) --
Optional settings for the transcription job. Use these settings to turn on speaker recognition, to set the maximum number of speakers that should be identified and to specify a custom vocabulary to use when processing the transcription job.
VocabularyName (string) --
The name of a vocabulary to use when processing the transcription job.
ShowSpeakerLabels (boolean) --
Determines whether the transcription job uses speaker recognition to identify different speakers in the input audio. Speaker recognition labels individual speakers in the audio file. If you set the ShowSpeakerLabels field to true, you must also set the maximum number of speaker labels MaxSpeakerLabels field.
You can't set both ShowSpeakerLabels and ChannelIdentification in the same request. If you set both, your request returns a BadRequestException .
MaxSpeakerLabels (integer) --
The maximum number of speakers to identify in the input audio. If there are more speakers in the audio than this number, multiple speakers are identified as a single speaker. If you specify the MaxSpeakerLabels field, you must set the ShowSpeakerLabels field to true.
ChannelIdentification (boolean) --
Instructs Amazon Transcribe to process each audio channel separately and then merge the transcription output of each channel into a single transcription.
Amazon Transcribe also produces a transcription of each item detected on an audio channel, including the start time and end time of the item and alternative transcriptions of the item including the confidence that Amazon Transcribe has in the transcription.
You can't set both ShowSpeakerLabels and ChannelIdentification in the same request. If you set both, your request returns a BadRequestException .
ShowAlternatives (boolean) --
Determines whether the transcription contains alternative transcriptions. If you set the ShowAlternatives field to true, you must also set the maximum number of alternatives to return in the MaxAlternatives field.
MaxAlternatives (integer) --
The number of alternative transcriptions that the service should return. If you specify the MaxAlternatives field, you must set the ShowAlternatives field to true.
VocabularyFilterName (string) --
The name of the vocabulary filter to use when transcribing the audio. The filter that you specify must have the same language code as the transcription job.
VocabularyFilterMethod (string) --
Set to mask to remove filtered text from the transcript and replace it with three asterisks ("***") as placeholder text. Set to remove to remove filtered text from the transcript without using placeholder text. Set to tag to mark the word in the transcription output that matches the vocabulary filter. When you set the filter method to tag , the words matching your vocabulary filter are not masked or removed.
ModelSettings (dict) --
An object containing the details of your custom language model.
LanguageModelName (string) --
The name of your custom language model.
JobExecutionSettings (dict) --
Provides information about how a transcription job is executed.
AllowDeferredExecution (boolean) --
Indicates whether a job should be queued by Amazon Transcribe when the concurrent execution limit is exceeded. When the AllowDeferredExecution field is true, jobs are queued and executed when the number of executing jobs falls below the concurrent execution limit. If the field is false, Amazon Transcribe returns a LimitExceededException exception.
Note that job queuing is enabled by default for call analytics jobs.
If you specify the AllowDeferredExecution field, you must specify the DataAccessRoleArn field.
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN), in the form arn:partition:service:region:account-id:resource-type/resource-id , of a role that has access to the S3 bucket that contains the input files. Amazon Transcribe assumes this role to read queued media files. If you have specified an output S3 bucket for the transcription results, this role should have access to the output bucket as well.
If you specify the AllowDeferredExecution field, you must specify the DataAccessRoleArn field.
ContentRedaction (dict) --
An object that describes content redaction settings for the transcription job.
RedactionType (string) --
Request parameter that defines the entities to be redacted. The only accepted value is PII .
RedactionOutput (string) --
The output transcript file stored in either the default S3 bucket or in a bucket you specify.
When you choose redacted Amazon Transcribe outputs only the redacted transcript.
When you choose redacted_and_unredacted Amazon Transcribe outputs both the redacted and unredacted transcripts.
IdentifyLanguage (boolean) --
A value that shows if automatic language identification was enabled for a transcription job.
LanguageOptions (list) --
An object that shows the optional array of languages inputted for transcription jobs with automatic language identification enabled.
(string) --
IdentifiedLanguageScore (float) --
A value between zero and one that Amazon Transcribe assigned to the language that it identified in the source audio. Larger values indicate that Amazon Transcribe has higher confidence in the language it identified.
Tags (list) --
A key:value pair assigned to a given transcription job.
(dict) --
A key:value pair that adds metadata to a resource used by Amazon Transcribe. For example, a tag with the key:value pair ‘Department’:’Sales’ might be added to a resource to indicate its use by your organization's sales department.
Key (string) --
The first part of a key:value pair that forms a tag associated with a given resource. For example, in the tag ‘Department’:’Sales’, the key is 'Department'.
Value (string) --
The second part of a key:value pair that forms a tag associated with a given resource. For example, in the tag ‘Department’:’Sales’, the value is 'Sales'.
Subtitles (dict) --
Generate subtitles for your batch transcription job.
Formats (list) --
Specify the output format for your subtitle file; if you select both SRT and VTT formats, two output files are genereated.
(string) --
SubtitleFileUris (list) --
Choose the output location for your subtitle file. This location must be an S3 bucket.
(string) --
LanguageIdSettings (dict) --
Language-specific settings that can be specified when language identification is enabled for your transcription job. These settings include VocabularyName , VocabularyFilterName , and LanguageModelName LanguageModelName.
(string) --
(dict) --
Language-specific settings that can be specified when language identification is enabled.
VocabularyName (string) --
The name of the vocabulary you want to use when processing your transcription job. The vocabulary you specify must have the same language code as the transcription job; if the languages don't match, the vocabulary won't be applied.
VocabularyFilterName (string) --
The name of the vocabulary filter you want to use when transcribing your audio. The filter you specify must have the same language code as the transcription job; if the languages don't match, the vocabulary filter won't be applied.
LanguageModelName (string) --
The name of the language model you want to use when transcribing your audio. The model you specify must have the same language code as the transcription job; if the languages don't match, the language model won't be applied.