Share via

TranscriptionClient Class

TranscriptionClient.

Constructor

TranscriptionClient(endpoint: str, credential: AzureKeyCredential | TokenCredential, **kwargs: Any)

Parameters

Name Description
endpoint
Required
str

Supported Cognitive Services endpoints (protocol and hostname, for example: https://westus.api.cognitive.microsoft.com). Required.
credential
Required
AzureKeyCredential or TokenCredential

Credential used to authenticate requests to the service. Is either a key credential type or a token credential type. Required.

Keyword-Only Parameters

Name Description
api_version
str

The API version to use for this operation. Default value is "2025-10-15". Note that overriding this default value may result in unsupported behavior.

Methods

close
send_request

Runs the network request through the client's chained policies.


>>> from azure.core.rest import HttpRequest
>>> request = HttpRequest("GET", "https://www.example.org/")
<HttpRequest [GET], url: 'https://www.example.org/'>
>>> response = client.send_request(request)
<HttpResponse: 200 OK>

For more information on this code flow, see https://aka.ms/azsdk/dpcodegen/python/send_request
transcribe

Transcribes the provided audio stream.
transcribe_from_url

Transcribes audio from a URL.

Use this method when the audio is hosted at a URL that the service can access. For transcribing local audio files or byte streams, use transcribe instead.

close 

close() -> None

send_request

Runs the network request through the client's chained policies.


>>> from azure.core.rest import HttpRequest
>>> request = HttpRequest("GET", "https://www.example.org/")
<HttpRequest [GET], url: 'https://www.example.org/'>
>>> response = client.send_request(request)
<HttpResponse: 200 OK>

For more information on this code flow, see https://aka.ms/azsdk/dpcodegen/python/send_request

send_request(request: HttpRequest, *, stream: bool = False, **kwargs: Any) -> HttpResponse

Parameters

Name Description
request
Required
HttpRequest

The network request you want to make. Required.

Keyword-Only Parameters

Name Description
stream
bool

Whether the response payload will be streamed. Defaults to False.

Default value: False

Returns

Type Description
HttpResponse

The response of your network call. Does not do error handling on your response.

transcribe

Transcribes the provided audio stream.

transcribe(body: TranscriptionContent | MutableMapping[str, Any], **kwargs: Any) -> TranscriptionResult

Parameters

Name Description
body
Required
TranscriptionContent or <xref:JSON>

The body of the multipart request. Is either a TranscriptionContent type or a JSON type. Required.

Returns

Type Description
TranscriptionResult

TranscriptionResult. The TranscriptionResult is compatible with MutableMapping

Exceptions

Type Description
HttpResponseError

transcribe_from_url

Transcribes audio from a URL.

Use this method when the audio is hosted at a URL that the service can access. For transcribing local audio files or byte streams, use transcribe instead.

transcribe_from_url(audio_url: str, *, options: TranscriptionOptions | None = None, **kwargs: Any) -> TranscriptionResult

Parameters

Name Description
audio_url
Required
str

The URL of the audio file to transcribe. The audio must be shorter than 2 hours in duration and smaller than 250 MB in size. Required.

Keyword-Only Parameters

Name Description
options
TranscriptionOptions

Optional transcription configuration. If provided, the audio_url parameter will override the audio_url field in the options object.

Default value: None

Returns

Type Description
TranscriptionResult

TranscriptionResult with the transcription text and phrases.

Exceptions

Type Description
HttpResponseError

Examples

Transcribe audio from a URL.


   from azure.core.credentials import AzureKeyCredential
   from azure.ai.transcription import TranscriptionClient
   from azure.ai.transcription.models import TranscriptionOptions

   # Get configuration from environment variables
   endpoint = os.environ["AZURE_SPEECH_ENDPOINT"]

   # We recommend using role-based access control (RBAC) for production scenarios
   api_key = os.environ.get("AZURE_SPEECH_API_KEY")
   if api_key:
       credential = AzureKeyCredential(api_key)
   else:
       from azure.identity import DefaultAzureCredential

       credential = DefaultAzureCredential()

   # Create the transcription client
   client = TranscriptionClient(endpoint=endpoint, credential=credential)

   # URL to your audio file (must be publicly accessible)
   audio_url = "https://example.com/path/to/audio.wav"
   # Configure transcription options
   options = TranscriptionOptions(locales=["en-US"])

   # Transcribe the audio from URL
   # The service will access and transcribe the audio directly from the URL
   result = client.transcribe_from_url(audio_url, options=options)

   # Print the transcription result
   print(f"Transcription: {result.combined_phrases[0].text}")

   # Print duration information
   if result.duration_milliseconds:
       print(f"Audio duration: {result.duration_milliseconds / 1000:.2f} seconds")