2020/04/29 - Amazon Transcribe Service - 5 new 3 updated api methods
Changes With this release, you can now use Amazon Transcribe to create medical custom vocabularies and use them in both medical real-time streaming and medical batch transcription jobs.
Creates a new custom vocabulary that you can use to change how Amazon Transcribe Medical transcribes your audio file.
See also: AWS API Documentation
Request Syntax
client.create_medical_vocabulary(
VocabularyName='string',
LanguageCode='en-US'|'es-US'|'en-AU'|'fr-CA'|'en-GB'|'de-DE'|'pt-BR'|'fr-FR'|'it-IT'|'ko-KR'|'es-ES'|'en-IN'|'hi-IN'|'ar-SA'|'ru-RU'|'zh-CN'|'nl-NL'|'id-ID'|'ta-IN'|'fa-IR'|'en-IE'|'en-AB'|'en-WL'|'pt-PT'|'te-IN'|'tr-TR'|'de-CH'|'he-IL'|'ms-MY'|'ja-JP'|'ar-AE',
VocabularyFileUri='string'
)
string
[REQUIRED]
The name of the custom vocabulary. This case-sensitive name must be unique within an AWS account. If you try to create a vocabulary with the same name as a previous vocabulary you will receive a ConflictException error.
string
[REQUIRED]
The language code used for the entries within your custom vocabulary. The language code of your custom vocabulary must match the language code of your transcription job. US English (en-US) is the only language code available for Amazon Transcribe Medical.
string
[REQUIRED]
The Amazon S3 location of the text file you use to define your custom vocabulary. The URI must be in the same AWS region as the API endpoint you're calling. Enter information about your VocabularyFileUri in the following format:
https://s3.<aws-region>.amazonaws.com/<bucket-name>/<keyprefix>/<objectkey>
This is an example of a vocabulary file uri location in Amazon S3:
https://s3.us-east-1.amazonaws.com/examplebucket/vocab.txt
For more information about S3 object names, see Object Keys in the Amazon S3 Developer Guide .
For more information about custom vocabularies, see Medical Custom Vocabularies.
dict
Response Syntax
{
'VocabularyName': 'string',
'LanguageCode': 'en-US'|'es-US'|'en-AU'|'fr-CA'|'en-GB'|'de-DE'|'pt-BR'|'fr-FR'|'it-IT'|'ko-KR'|'es-ES'|'en-IN'|'hi-IN'|'ar-SA'|'ru-RU'|'zh-CN'|'nl-NL'|'id-ID'|'ta-IN'|'fa-IR'|'en-IE'|'en-AB'|'en-WL'|'pt-PT'|'te-IN'|'tr-TR'|'de-CH'|'he-IL'|'ms-MY'|'ja-JP'|'ar-AE',
'VocabularyState': 'PENDING'|'READY'|'FAILED',
'LastModifiedTime': datetime(2015, 1, 1),
'FailureReason': 'string'
}
Response Structure
(dict) --
VocabularyName (string) --
The name of the vocabulary. The name must be unique within an AWS account. It is also case-sensitive.
LanguageCode (string) --
The language code you chose to describe the entries in your custom vocabulary. US English (en-US) is the only valid language code for Amazon Transcribe Medical.
VocabularyState (string) --
The processing state of your custom vocabulary in Amazon Transcribe Medical. If the state is READY you can use the vocabulary in a StartMedicalTranscriptionJob request.
LastModifiedTime (datetime) --
The date and time you created the vocabulary.
FailureReason (string) --
If the VocabularyState field is FAILED , this field contains information about why the job failed.
Deletes a vocabulary from Amazon Transcribe Medical.
See also: AWS API Documentation
Request Syntax
client.delete_medical_vocabulary(
VocabularyName='string'
)
string
[REQUIRED]
The name of the vocabulary you are choosing to delete.
None
Updates an existing vocabulary with new values in a different text file. The UpdateMedicalVocabulary operation overwrites all of the existing information with the values that you provide in the request.
See also: AWS API Documentation
Request Syntax
client.update_medical_vocabulary(
VocabularyName='string',
LanguageCode='en-US'|'es-US'|'en-AU'|'fr-CA'|'en-GB'|'de-DE'|'pt-BR'|'fr-FR'|'it-IT'|'ko-KR'|'es-ES'|'en-IN'|'hi-IN'|'ar-SA'|'ru-RU'|'zh-CN'|'nl-NL'|'id-ID'|'ta-IN'|'fa-IR'|'en-IE'|'en-AB'|'en-WL'|'pt-PT'|'te-IN'|'tr-TR'|'de-CH'|'he-IL'|'ms-MY'|'ja-JP'|'ar-AE',
VocabularyFileUri='string'
)
string
[REQUIRED]
The name of the vocabulary to update. The name is case-sensitive. If you try to update a vocabulary with the same name as a previous vocabulary you will receive a ConflictException error.
string
[REQUIRED]
The language code of the entries in the updated vocabulary. US English (en-US) is the only valid language code in Amazon Transcribe Medical.
string
The Amazon S3 location of the text file containing the definition of the custom vocabulary. The URI must be in the same AWS region as the API endpoint you are calling. You can see the fields you need to enter for you Amazon S3 location in the example URI here:
https://s3.<aws-region>.amazonaws.com/<bucket-name>/<keyprefix>/<objectkey>
For example:
https://s3.us-east-1.amazonaws.com/examplebucket/vocab.txt
For more information about S3 object names, see Object Keys in the Amazon S3 Developer Guide .
For more information about custom vocabularies in Amazon Transcribe Medical, see Medical Custom Vocabularies.
dict
Response Syntax
{
'VocabularyName': 'string',
'LanguageCode': 'en-US'|'es-US'|'en-AU'|'fr-CA'|'en-GB'|'de-DE'|'pt-BR'|'fr-FR'|'it-IT'|'ko-KR'|'es-ES'|'en-IN'|'hi-IN'|'ar-SA'|'ru-RU'|'zh-CN'|'nl-NL'|'id-ID'|'ta-IN'|'fa-IR'|'en-IE'|'en-AB'|'en-WL'|'pt-PT'|'te-IN'|'tr-TR'|'de-CH'|'he-IL'|'ms-MY'|'ja-JP'|'ar-AE',
'LastModifiedTime': datetime(2015, 1, 1),
'VocabularyState': 'PENDING'|'READY'|'FAILED'
}
Response Structure
(dict) --
VocabularyName (string) --
The name of the updated vocabulary.
LanguageCode (string) --
The language code for the text file used to update the custom vocabulary. US English (en-US) is the only language supported in Amazon Transcribe Medical.
LastModifiedTime (datetime) --
The date and time the vocabulary was updated.
VocabularyState (string) --
The processing state of the update to the vocabulary. When the VocabularyState field is READY the vocabulary is ready to be used in a StartMedicalTranscriptionJob request.
Returns a list of vocabularies that match the specified criteria. You get the entire list of vocabularies if you don't enter a value in any of the request parameters.
See also: AWS API Documentation
Request Syntax
client.list_medical_vocabularies(
NextToken='string',
MaxResults=123,
StateEquals='PENDING'|'READY'|'FAILED',
NameContains='string'
)
string
If the result of your previous request to ListMedicalVocabularies was truncated, include the NextToken to fetch the next set of jobs.
integer
The maximum number of vocabularies to return in the response.
string
When specified, only returns vocabularies with the VocabularyState equal to the specified vocabulary state.
string
Returns vocabularies in the list whose name contains the specified string. The search is case-insensitive, ListMedicalVocabularies returns both "vocabularyname" and "VocabularyName" in the response list.
dict
Response Syntax
{
'Status': 'PENDING'|'READY'|'FAILED',
'NextToken': 'string',
'Vocabularies': [
{
'VocabularyName': 'string',
'LanguageCode': 'en-US'|'es-US'|'en-AU'|'fr-CA'|'en-GB'|'de-DE'|'pt-BR'|'fr-FR'|'it-IT'|'ko-KR'|'es-ES'|'en-IN'|'hi-IN'|'ar-SA'|'ru-RU'|'zh-CN'|'nl-NL'|'id-ID'|'ta-IN'|'fa-IR'|'en-IE'|'en-AB'|'en-WL'|'pt-PT'|'te-IN'|'tr-TR'|'de-CH'|'he-IL'|'ms-MY'|'ja-JP'|'ar-AE',
'LastModifiedTime': datetime(2015, 1, 1),
'VocabularyState': 'PENDING'|'READY'|'FAILED'
},
]
}
Response Structure
(dict) --
Status (string) --
The requested vocabulary state.
NextToken (string) --
The ListMedicalVocabularies operation returns a page of vocabularies at a time. The maximum size of the page is set by the MaxResults parameter. If there are more jobs in the list than the page size, Amazon Transcribe Medical returns the NextPage token. Include the token in the next request to the ListMedicalVocabularies operation to return the next page of jobs.
Vocabularies (list) --
A list of objects that describe the vocabularies that match the search criteria in the request.
(dict) --
Provides information about a custom vocabulary.
VocabularyName (string) --
The name of the vocabulary.
LanguageCode (string) --
The language code of the vocabulary entries.
LastModifiedTime (datetime) --
The date and time that the vocabulary was last modified.
VocabularyState (string) --
The processing state of the vocabulary. If the state is READY you can use the vocabulary in a StartTranscriptionJob request.
Retrieve information about a medical vocabulary.
See also: AWS API Documentation
Request Syntax
client.get_medical_vocabulary(
VocabularyName='string'
)
string
[REQUIRED]
The name of the vocabulary you are trying to get information about. The value you enter for this request is case-sensitive.
dict
Response Syntax
{
'VocabularyName': 'string',
'LanguageCode': 'en-US'|'es-US'|'en-AU'|'fr-CA'|'en-GB'|'de-DE'|'pt-BR'|'fr-FR'|'it-IT'|'ko-KR'|'es-ES'|'en-IN'|'hi-IN'|'ar-SA'|'ru-RU'|'zh-CN'|'nl-NL'|'id-ID'|'ta-IN'|'fa-IR'|'en-IE'|'en-AB'|'en-WL'|'pt-PT'|'te-IN'|'tr-TR'|'de-CH'|'he-IL'|'ms-MY'|'ja-JP'|'ar-AE',
'VocabularyState': 'PENDING'|'READY'|'FAILED',
'LastModifiedTime': datetime(2015, 1, 1),
'FailureReason': 'string',
'DownloadUri': 'string'
}
Response Structure
(dict) --
VocabularyName (string) --
The valid name that Amazon Transcribe Medical returns.
LanguageCode (string) --
The valid language code returned for your vocabulary entries.
VocabularyState (string) --
The processing state of the vocabulary.
LastModifiedTime (datetime) --
The date and time the vocabulary was last modified with a text file different from what was previously used.
FailureReason (string) --
If the VocabularyState is FAILED , this field contains information about why the job failed.
DownloadUri (string) --
The Amazon S3 location where the vocabulary is stored. Use this URI to get the contents of the vocabulary. You can download your vocabulary from the URI for a limited time.
{'MedicalTranscriptionJob': {'Settings': {'VocabularyName': 'string'}}}
Returns information about a transcription job from Amazon Transcribe Medical. To see the status of the job, check the TranscriptionJobStatus field. If the status is COMPLETED , the job is finished. You find the results of the completed job in the TranscriptFileUri field.
See also: AWS API Documentation
Request Syntax
client.get_medical_transcription_job(
MedicalTranscriptionJobName='string'
)
string
[REQUIRED]
The name of the medical transcription job.
dict
Response Syntax
{
'MedicalTranscriptionJob': {
'MedicalTranscriptionJobName': 'string',
'TranscriptionJobStatus': 'QUEUED'|'IN_PROGRESS'|'FAILED'|'COMPLETED',
'LanguageCode': 'en-US'|'es-US'|'en-AU'|'fr-CA'|'en-GB'|'de-DE'|'pt-BR'|'fr-FR'|'it-IT'|'ko-KR'|'es-ES'|'en-IN'|'hi-IN'|'ar-SA'|'ru-RU'|'zh-CN'|'nl-NL'|'id-ID'|'ta-IN'|'fa-IR'|'en-IE'|'en-AB'|'en-WL'|'pt-PT'|'te-IN'|'tr-TR'|'de-CH'|'he-IL'|'ms-MY'|'ja-JP'|'ar-AE',
'MediaSampleRateHertz': 123,
'MediaFormat': 'mp3'|'mp4'|'wav'|'flac',
'Media': {
'MediaFileUri': 'string'
},
'Transcript': {
'TranscriptFileUri': 'string'
},
'StartTime': datetime(2015, 1, 1),
'CreationTime': datetime(2015, 1, 1),
'CompletionTime': datetime(2015, 1, 1),
'FailureReason': 'string',
'Settings': {
'ShowSpeakerLabels': True|False,
'MaxSpeakerLabels': 123,
'ChannelIdentification': True|False,
'ShowAlternatives': True|False,
'MaxAlternatives': 123,
'VocabularyName': 'string'
},
'Specialty': 'PRIMARYCARE',
'Type': 'CONVERSATION'|'DICTATION'
}
}
Response Structure
(dict) --
MedicalTranscriptionJob (dict) --
An object that contains the results of the medical transcription job.
MedicalTranscriptionJobName (string) --
The name for a given medical transcription job.
TranscriptionJobStatus (string) --
The completion status of a medical transcription job.
LanguageCode (string) --
The language code for the language spoken in the source audio file. US English (en-US) is the only supported language for medical transcriptions. Any other value you enter for language code results in a BadRequestException error.
MediaSampleRateHertz (integer) --
The sample rate, in Hertz, of the source audio containing medical information.
If you don't specify the sample rate, Amazon Transcribe Medical determines it for you. If you choose to specify the sample rate, it must match the rate detected by Amazon Transcribe Medical. In most cases, you should leave the MediaSampleHertz blank and let Amazon Transcribe Medical determine the sample rate.
MediaFormat (string) --
The format of the input media file.
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:
s3://<bucket-name>/<keyprefix>/<objectkey>
For example:
s3://examplebucket/example.mp4
s3://examplebucket/mediadocs/example.mp4
For more information about S3 object names, see Object Keys in the Amazon S3 Developer Guide .
Transcript (dict) --
An object that contains the MedicalTranscript . The MedicalTranscript contains the TranscriptFileUri .
TranscriptFileUri (string) --
The S3 object location of the medical transcript.
Use this URI to access the medical transcript. This URI points to the S3 bucket you created to store the medical transcript.
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 was completed.
FailureReason (string) --
If the TranscriptionJobStatus field is FAILED , this field contains information about why the job failed.
The FailureReason field contains 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 8000 and 48000 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 Guidlines 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
Settings (dict) --
Object that contains object.
ShowSpeakerLabels (boolean) --
Determines whether the transcription job uses speaker recognition to identify different speakers in the input audio. Speaker recongition 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 in the 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 Medical to process each audio channel separately and then merge the transcription output of each channel into a single transcription.
Amazon Transcribe Medical 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 item. The alternative transcriptions also come with confidence scores provided by Amazon Transcribe Medical.
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 alternative transcripts are generated along with the transcript that has the highest confidence. If you set ShowAlternatives field to true, you must also set the maximum number of alternatives to return in the MaxAlternatives field.
MaxAlternatives (integer) --
The maximum number of alternatives that you tell the service to return. If you specify the MaxAlternatives field, you must set the ShowAlternatives field to true.
VocabularyName (string) --
The name of the vocabulary to use when processing a medical transcription job.
Specialty (string) --
The medical specialty of any clinicians providing a dictation or having a conversation. PRIMARYCARE is the only available setting for this object. This specialty enables you to generate transcriptions for the following medical fields:
Family Medicine
Type (string) --
The type of speech in the transcription job. CONVERSATION is generally used for patient-physician dialogues. DICTATION is the setting for physicians speaking their notes after seeing a patient. For more information, see how-it-works-med
{'Status': {'READY', 'PENDING'}}
Returns a list of vocabularies that match the specified criteria. If no criteria are specified, returns the entire list of vocabularies.
See also: AWS API Documentation
Request Syntax
client.list_vocabularies(
NextToken='string',
MaxResults=123,
StateEquals='PENDING'|'READY'|'FAILED',
NameContains='string'
)
string
If the result of the previous request to ListVocabularies was truncated, include the NextToken to fetch the next set of jobs.
integer
The maximum number of vocabularies to return in the response. If there are fewer results in the list, this response contains only the actual results.
string
When specified, only returns vocabularies with the VocabularyState field equal to the specified state.
string
When specified, the vocabularies returned in the list are limited to vocabularies whose name contains the specified string. The search is case-insensitive, ListVocabularies returns both "vocabularyname" and "VocabularyName" in the response list.
dict
Response Syntax
{
'Status': 'PENDING'|'READY'|'FAILED',
'NextToken': 'string',
'Vocabularies': [
{
'VocabularyName': 'string',
'LanguageCode': 'en-US'|'es-US'|'en-AU'|'fr-CA'|'en-GB'|'de-DE'|'pt-BR'|'fr-FR'|'it-IT'|'ko-KR'|'es-ES'|'en-IN'|'hi-IN'|'ar-SA'|'ru-RU'|'zh-CN'|'nl-NL'|'id-ID'|'ta-IN'|'fa-IR'|'en-IE'|'en-AB'|'en-WL'|'pt-PT'|'te-IN'|'tr-TR'|'de-CH'|'he-IL'|'ms-MY'|'ja-JP'|'ar-AE',
'LastModifiedTime': datetime(2015, 1, 1),
'VocabularyState': 'PENDING'|'READY'|'FAILED'
},
]
}
Response Structure
(dict) --
Status (string) --
The requested vocabulary state.
NextToken (string) --
The ListVocabularies operation returns a page of vocabularies at a time. The maximum size of the page is set by the MaxResults parameter. If there are more jobs in the list than the page size, Amazon Transcribe returns the NextPage token. Include the token in the next request to the ListVocabularies operation to return in the next page of jobs.
Vocabularies (list) --
A list of objects that describe the vocabularies that match the search criteria in the request.
(dict) --
Provides information about a custom vocabulary.
VocabularyName (string) --
The name of the vocabulary.
LanguageCode (string) --
The language code of the vocabulary entries.
LastModifiedTime (datetime) --
The date and time that the vocabulary was last modified.
VocabularyState (string) --
The processing state of the vocabulary. If the state is READY you can use the vocabulary in a StartTranscriptionJob request.
{'Settings': {'VocabularyName': 'string'}}
Response {'MedicalTranscriptionJob': {'Settings': {'VocabularyName': 'string'}}}
Start a batch job to transcribe medical speech to text.
See also: AWS API Documentation
Request Syntax
client.start_medical_transcription_job(
MedicalTranscriptionJobName='string',
LanguageCode='en-US'|'es-US'|'en-AU'|'fr-CA'|'en-GB'|'de-DE'|'pt-BR'|'fr-FR'|'it-IT'|'ko-KR'|'es-ES'|'en-IN'|'hi-IN'|'ar-SA'|'ru-RU'|'zh-CN'|'nl-NL'|'id-ID'|'ta-IN'|'fa-IR'|'en-IE'|'en-AB'|'en-WL'|'pt-PT'|'te-IN'|'tr-TR'|'de-CH'|'he-IL'|'ms-MY'|'ja-JP'|'ar-AE',
MediaSampleRateHertz=123,
MediaFormat='mp3'|'mp4'|'wav'|'flac',
Media={
'MediaFileUri': 'string'
},
OutputBucketName='string',
OutputEncryptionKMSKeyId='string',
Settings={
'ShowSpeakerLabels': True|False,
'MaxSpeakerLabels': 123,
'ChannelIdentification': True|False,
'ShowAlternatives': True|False,
'MaxAlternatives': 123,
'VocabularyName': 'string'
},
Specialty='PRIMARYCARE',
Type='CONVERSATION'|'DICTATION'
)
string
[REQUIRED]
The name of the medical transcription job. You can't use the strings "." or ".." by themselves as the job name. The name must also be unique within an AWS account. If you try to create a medical transcription job with the same name as a previous medical transcription job you will receive a ConflictException error.
string
[REQUIRED]
The language code for the language spoken in the input media file. US English (en-US) is the valid value for medical transcription jobs. Any other value you enter for language code results in a BadRequestException error.
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 Medical determines the sample rate. If you specify the sample rate, it must match the rate detected by Amazon Transcribe Medical. In most cases, you should leave the MediaSampleRateHertz field blank and let Amazon Transcribe Medical determine the sample rate.
string
The audio format of the input media file.
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:
s3://<bucket-name>/<keyprefix>/<objectkey>
For example:
s3://examplebucket/example.mp4
s3://examplebucket/mediadocs/example.mp4
For more information about S3 object names, see Object Keys in the Amazon S3 Developer Guide .
string
[REQUIRED]
The Amazon S3 location where the transcription is stored.
You must set OutputBucketName for Amazon Transcribe Medical to store the transcription results. Your transcript appears in the S3 location you specify. When you call the GetMedicalTranscriptionJob, the operation returns this location in the TranscriptFileUri field. The S3 bucket must have permissions that allow Amazon Transcribe Medical to put files in the bucket. For more information, see Permissions Required for IAM User Roles.
You can specify an AWS 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 Medical uses the default Amazon S3 key for server-side encryption of transcripts that are placed in your S3 bucket.
string
The Amazon Resource Name (ARN) of the AWS Key Management Service (KMS) key used to encrypt the output of the transcription job. The user calling the StartMedicalTranscriptionJob operation must have permission to use the specified KMS key.
You 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 in the current account or another account: "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 medical 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
Optional settings for the medical transcription job.
ShowSpeakerLabels (boolean) --
Determines whether the transcription job uses speaker recognition to identify different speakers in the input audio. Speaker recongition 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 in the 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 Medical to process each audio channel separately and then merge the transcription output of each channel into a single transcription.
Amazon Transcribe Medical 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 item. The alternative transcriptions also come with confidence scores provided by Amazon Transcribe Medical.
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 alternative transcripts are generated along with the transcript that has the highest confidence. If you set ShowAlternatives field to true, you must also set the maximum number of alternatives to return in the MaxAlternatives field.
MaxAlternatives (integer) --
The maximum number of alternatives that you tell the service to return. If you specify the MaxAlternatives field, you must set the ShowAlternatives field to true.
VocabularyName (string) --
The name of the vocabulary to use when processing a medical transcription job.
string
[REQUIRED]
The medical specialty of any clinician speaking in the input media.
string
[REQUIRED]
The type of speech in the input audio. CONVERSATION refers to conversations between two or more speakers, e.g., a conversations between doctors and patients. DICTATION refers to single-speaker dictated speech, e.g., for clinical notes.
dict
Response Syntax
{
'MedicalTranscriptionJob': {
'MedicalTranscriptionJobName': 'string',
'TranscriptionJobStatus': 'QUEUED'|'IN_PROGRESS'|'FAILED'|'COMPLETED',
'LanguageCode': 'en-US'|'es-US'|'en-AU'|'fr-CA'|'en-GB'|'de-DE'|'pt-BR'|'fr-FR'|'it-IT'|'ko-KR'|'es-ES'|'en-IN'|'hi-IN'|'ar-SA'|'ru-RU'|'zh-CN'|'nl-NL'|'id-ID'|'ta-IN'|'fa-IR'|'en-IE'|'en-AB'|'en-WL'|'pt-PT'|'te-IN'|'tr-TR'|'de-CH'|'he-IL'|'ms-MY'|'ja-JP'|'ar-AE',
'MediaSampleRateHertz': 123,
'MediaFormat': 'mp3'|'mp4'|'wav'|'flac',
'Media': {
'MediaFileUri': 'string'
},
'Transcript': {
'TranscriptFileUri': 'string'
},
'StartTime': datetime(2015, 1, 1),
'CreationTime': datetime(2015, 1, 1),
'CompletionTime': datetime(2015, 1, 1),
'FailureReason': 'string',
'Settings': {
'ShowSpeakerLabels': True|False,
'MaxSpeakerLabels': 123,
'ChannelIdentification': True|False,
'ShowAlternatives': True|False,
'MaxAlternatives': 123,
'VocabularyName': 'string'
},
'Specialty': 'PRIMARYCARE',
'Type': 'CONVERSATION'|'DICTATION'
}
}
Response Structure
(dict) --
MedicalTranscriptionJob (dict) --
A batch job submitted to transcribe medical speech to text.
MedicalTranscriptionJobName (string) --
The name for a given medical transcription job.
TranscriptionJobStatus (string) --
The completion status of a medical transcription job.
LanguageCode (string) --
The language code for the language spoken in the source audio file. US English (en-US) is the only supported language for medical transcriptions. Any other value you enter for language code results in a BadRequestException error.
MediaSampleRateHertz (integer) --
The sample rate, in Hertz, of the source audio containing medical information.
If you don't specify the sample rate, Amazon Transcribe Medical determines it for you. If you choose to specify the sample rate, it must match the rate detected by Amazon Transcribe Medical. In most cases, you should leave the MediaSampleHertz blank and let Amazon Transcribe Medical determine the sample rate.
MediaFormat (string) --
The format of the input media file.
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:
s3://<bucket-name>/<keyprefix>/<objectkey>
For example:
s3://examplebucket/example.mp4
s3://examplebucket/mediadocs/example.mp4
For more information about S3 object names, see Object Keys in the Amazon S3 Developer Guide .
Transcript (dict) --
An object that contains the MedicalTranscript . The MedicalTranscript contains the TranscriptFileUri .
TranscriptFileUri (string) --
The S3 object location of the medical transcript.
Use this URI to access the medical transcript. This URI points to the S3 bucket you created to store the medical transcript.
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 was completed.
FailureReason (string) --
If the TranscriptionJobStatus field is FAILED , this field contains information about why the job failed.
The FailureReason field contains 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 8000 and 48000 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 Guidlines 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
Settings (dict) --
Object that contains object.
ShowSpeakerLabels (boolean) --
Determines whether the transcription job uses speaker recognition to identify different speakers in the input audio. Speaker recongition 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 in the 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 Medical to process each audio channel separately and then merge the transcription output of each channel into a single transcription.
Amazon Transcribe Medical 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 item. The alternative transcriptions also come with confidence scores provided by Amazon Transcribe Medical.
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 alternative transcripts are generated along with the transcript that has the highest confidence. If you set ShowAlternatives field to true, you must also set the maximum number of alternatives to return in the MaxAlternatives field.
MaxAlternatives (integer) --
The maximum number of alternatives that you tell the service to return. If you specify the MaxAlternatives field, you must set the ShowAlternatives field to true.
VocabularyName (string) --
The name of the vocabulary to use when processing a medical transcription job.
Specialty (string) --
The medical specialty of any clinicians providing a dictation or having a conversation. PRIMARYCARE is the only available setting for this object. This specialty enables you to generate transcriptions for the following medical fields:
Family Medicine
Type (string) --
The type of speech in the transcription job. CONVERSATION is generally used for patient-physician dialogues. DICTATION is the setting for physicians speaking their notes after seeing a patient. For more information, see how-it-works-med