Skip to content

start_medical_stream_transcription

Operation

Async only

This operation uses an event stream, so only the asynchronous client supports it.

start_medical_stream_transcription async

start_medical_stream_transcription(request: StartMedicalStreamTranscriptionInput | StartMedicalStreamTranscriptionInputDict | None = None, /, *, plugins: list[Plugin] | None = None, **kwargs: Unpack[StartMedicalStreamTranscriptionInputDict]) -> AsyncDuplexEventStream[AudioStream, MedicalTranscriptResultStream, StartMedicalStreamTranscriptionOutput]

Starts a bidirectional HTTP/2 or WebSocket stream where audio is streamed to Amazon Transcribe Medical and the transcription results are streamed to your application.

The following parameters are required:

  • language-code

  • media-encoding

  • sample-rate

For more information on streaming with Amazon Transcribe Medical, see Transcribing streaming audio.

Parameters:

Name Type Description Default
request StartMedicalStreamTranscriptionInput | StartMedicalStreamTranscriptionInputDict | None

The input as a model or dictionary. Pass this or keyword arguments, not both.

None
plugins list[Plugin] | None

A list of callables that modify the configuration dynamically. Changes made by these plugins only apply for the duration of the operation execution and will not affect any other operation invocations.

None
**kwargs Unpack[StartMedicalStreamTranscriptionInputDict]

The input fields as keyword arguments.

{}

Returns:

Type Description
AsyncDuplexEventStream[AudioStream, MedicalTranscriptResultStream, StartMedicalStreamTranscriptionOutput]

An AsyncDuplexEventStream for bidirectional streaming.

Input

Pass the input as keyword arguments, a positional dictionary, or a positional model object. Pass plugins separately as a keyword argument.

StartMedicalStreamTranscriptionInputDict

Bases: TypedDict

Dictionary form of StartMedicalStreamTranscriptionInput.

Attributes

content_identification_type instance-attribute
content_identification_type: str | None

Labels all personal health information (PHI) identified in your transcript.

Content identification is performed at the segment level; PHI is flagged upon complete transcription of an audio segment.

For more information, see Identifying personal health information (PHI) in a transcription.

enable_channel_identification instance-attribute
enable_channel_identification: bool | None

Enables channel identification in multi-channel audio.

Channel identification transcribes the audio on each channel independently, then appends the output for each channel into one transcript.

If you have multi-channel audio and do not enable channel identification, your audio is transcribed in a continuous manner and your transcript is not separated by channel.

If you include EnableChannelIdentification in your request, you must also include NumberOfChannels.

For more information, see Transcribing multi-channel audio.

language_code instance-attribute
language_code: Required[str]

Specify the language code that represents the language spoken in your audio.

Warning

Amazon Transcribe Medical only supports US English (en-US).

media_encoding instance-attribute
media_encoding: Required[str]

Specify the encoding used for the input audio. Supported formats are:

  • FLAC

  • OPUS-encoded audio in an Ogg container

  • PCM (only signed 16-bit little-endian audio formats, which does not include WAV)

For more information, see Media formats.

media_sample_rate_hertz instance-attribute
media_sample_rate_hertz: Required[int]

The sample rate of the input audio (in hertz). Amazon Transcribe Medical supports a range from 16,000 Hz to 48,000 Hz. Note that the sample rate you specify must match that of your audio.

number_of_channels instance-attribute
number_of_channels: int | None

Specify the number of channels in your audio stream. This value must be 2, as only two channels are supported. If your audio doesn't contain multiple channels, do not include this parameter in your request.

If you include NumberOfChannels in your request, you must also include EnableChannelIdentification.

session_id instance-attribute
session_id: str | None

Specify a name for your transcription session. If you don't include this parameter in your request, Amazon Transcribe Medical generates an ID and returns it in the response.

show_speaker_label instance-attribute
show_speaker_label: bool | None

Enables speaker partitioning (diarization) in your transcription output. Speaker partitioning labels the speech from individual speakers in your media file.

For more information, see Partitioning speakers (diarization).

specialty instance-attribute
specialty: Required[str]

Specify the medical specialty contained in your audio.

type instance-attribute
type: Required[str]

Specify the type of input audio. For example, choose DICTATION for a provider dictating patient notes and CONVERSATION for a dialogue between a patient and a medical professional.

vocabulary_name instance-attribute
vocabulary_name: str | None

Specify the name of the custom vocabulary that you want to use when processing your transcription. Note that vocabulary names are case sensitive.

StartMedicalStreamTranscriptionInput dataclass

Bases: _SerdeShape

Dataclass for StartMedicalStreamTranscriptionInput structure.

Attributes

content_identification_type class-attribute instance-attribute
content_identification_type: str | None = ...

Labels all personal health information (PHI) identified in your transcript.

Content identification is performed at the segment level; PHI is flagged upon complete transcription of an audio segment.

For more information, see Identifying personal health information (PHI) in a transcription.

enable_channel_identification class-attribute instance-attribute
enable_channel_identification: bool = ...

Enables channel identification in multi-channel audio.

Channel identification transcribes the audio on each channel independently, then appends the output for each channel into one transcript.

If you have multi-channel audio and do not enable channel identification, your audio is transcribed in a continuous manner and your transcript is not separated by channel.

If you include EnableChannelIdentification in your request, you must also include NumberOfChannels.

For more information, see Transcribing multi-channel audio.

language_code class-attribute instance-attribute
language_code: str | None = ...

Specify the language code that represents the language spoken in your audio.

Warning

Amazon Transcribe Medical only supports US English (en-US).

media_encoding class-attribute instance-attribute
media_encoding: str | None = ...

Specify the encoding used for the input audio. Supported formats are:

  • FLAC

  • OPUS-encoded audio in an Ogg container

  • PCM (only signed 16-bit little-endian audio formats, which does not include WAV)

For more information, see Media formats.

media_sample_rate_hertz class-attribute instance-attribute
media_sample_rate_hertz: int | None = ...

The sample rate of the input audio (in hertz). Amazon Transcribe Medical supports a range from 16,000 Hz to 48,000 Hz. Note that the sample rate you specify must match that of your audio.

number_of_channels class-attribute instance-attribute
number_of_channels: int | None = ...

Specify the number of channels in your audio stream. This value must be 2, as only two channels are supported. If your audio doesn't contain multiple channels, do not include this parameter in your request.

If you include NumberOfChannels in your request, you must also include EnableChannelIdentification.

session_id class-attribute instance-attribute
session_id: str | None = ...

Specify a name for your transcription session. If you don't include this parameter in your request, Amazon Transcribe Medical generates an ID and returns it in the response.

show_speaker_label class-attribute instance-attribute
show_speaker_label: bool = ...

Enables speaker partitioning (diarization) in your transcription output. Speaker partitioning labels the speech from individual speakers in your media file.

For more information, see Partitioning speakers (diarization).

specialty class-attribute instance-attribute
specialty: str | None = ...

Specify the medical specialty contained in your audio.

type class-attribute instance-attribute
type: str | None = ...

Specify the type of input audio. For example, choose DICTATION for a provider dictating patient notes and CONVERSATION for a dialogue between a patient and a medical professional.

vocabulary_name class-attribute instance-attribute
vocabulary_name: str | None = ...

Specify the name of the custom vocabulary that you want to use when processing your transcription. Note that vocabulary names are case sensitive.

Output

This operation returns an AsyncDuplexEventStream for bidirectional streaming.

Event Stream Structure

Input Event Type

AudioStream

Output Event Type

MedicalTranscriptResultStream

Initial Response Structure

StartMedicalStreamTranscriptionOutput dataclass

Bases: _SerdeShape

Dataclass for StartMedicalStreamTranscriptionOutput structure.

Attributes
content_identification_type class-attribute instance-attribute
content_identification_type: str | None = ...

Shows whether content identification was enabled for your transcription.

enable_channel_identification class-attribute instance-attribute
enable_channel_identification: bool = ...

Shows whether channel identification was enabled for your transcription.

language_code class-attribute instance-attribute
language_code: str | None = ...

Provides the language code that you specified in your request. This must be en-US.

media_encoding class-attribute instance-attribute
media_encoding: str | None = ...

Provides the media encoding you specified in your request.

media_sample_rate_hertz class-attribute instance-attribute
media_sample_rate_hertz: int | None = ...

Provides the sample rate that you specified in your request.

number_of_channels class-attribute instance-attribute
number_of_channels: int | None = ...

Provides the number of channels that you specified in your request.

request_id class-attribute instance-attribute
request_id: str | None = ...

Provides the identifier for your streaming request.

response_metadata class-attribute instance-attribute
response_metadata: ResponseMetadata = ...

Metadata about the response that produced this output. Use this to recover the request identifiers a service's support team needs in order to investigate a call. Members of the metadata are individually optional.

session_id class-attribute instance-attribute
session_id: str | None = ...

Provides the identifier for your transcription session.

show_speaker_label class-attribute instance-attribute
show_speaker_label: bool = ...

Shows whether speaker partitioning was enabled for your transcription.

specialty class-attribute instance-attribute
specialty: str | None = ...

Provides the medical specialty that you specified in your request.

type class-attribute instance-attribute
type: str | None = ...

Provides the type of audio you specified in your request.

vocabulary_name class-attribute instance-attribute
vocabulary_name: str | None = ...

Provides the name of the custom vocabulary that you specified in your request.