Wangamber/transcription update samples

sdk/cognitiveservices/azure-ai-transcription/CHANGELOG.md

@@ -1,5 +1,15 @@
 # Release History
 
+## 1.0.0b3 (2026-02-04)
+
+### Features Added
+
+- Enhanced Mode now automatically sets `enabled=True` when `task`, `target_language`, or `prompt` are specified
+
+### Bugs Fixed
+
+- Fixed Enhanced Mode not being activated when using `EnhancedModeProperties` without explicitly setting `enabled=True`
+
 ## 1.0.0b2 (2025-12-19)
 
 ### Bugs Fixed

sdk/cognitiveservices/azure-ai-transcription/README.md

@@ -149,10 +149,18 @@ from azure.ai.transcription.models import TranscriptionContent, TranscriptionOpt
 
 # Get configuration from environment variables
 endpoint = os.environ["AZURE_SPEECH_ENDPOINT"]
-api_key = os.environ["AZURE_SPEECH_API_KEY"]
+
+# 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=AzureKeyCredential(api_key))
+client = TranscriptionClient(endpoint=endpoint, credential=credential)
 
 # Path to your audio file
 import pathlib
@@ -197,10 +205,18 @@ from azure.ai.transcription.models import TranscriptionOptions
 
 # Get configuration from environment variables
 endpoint = os.environ["AZURE_SPEECH_ENDPOINT"]
-api_key = os.environ["AZURE_SPEECH_API_KEY"]
+
+# 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=AzureKeyCredential(api_key))
+client = TranscriptionClient(endpoint=endpoint, credential=credential)
 
 # URL to your audio file (must be publicly accessible)
 audio_url = "https://example.com/path/to/audio.wav"
@@ -238,31 +254,29 @@ from azure.ai.transcription.models import (
 
 # Get configuration from environment variables
 endpoint = os.environ["AZURE_SPEECH_ENDPOINT"]
-api_key = os.environ["AZURE_SPEECH_API_KEY"]
+
+# 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=AzureKeyCredential(api_key))
+client = TranscriptionClient(endpoint=endpoint, credential=credential)
 
 # Path to your audio file
-import pathlib
-
 audio_file_path = pathlib.Path(__file__).parent / "assets" / "audio.wav"
 
 # Open and read the audio file
 with open(audio_file_path, "rb") as audio_file:
-    # Create enhanced mode properties
-    # Enable enhanced mode for advanced processing capabilities
-    enhanced_mode = EnhancedModeProperties(
-        task="translation",  # Specify the task type (e.g., "translation", "summarization")
-        target_language="es-ES",  # Target language for translation
-        prompt=[
-            "Translate the following audio to Spanish",
-            "Focus on technical terminology",
-        ],  # Optional prompts to guide the enhanced mode
-    )
+    # Enhanced mode is automatically enabled when task is specified
+    enhanced_mode = EnhancedModeProperties(task="transcribe")
 
     # Create transcription options with enhanced mode
-    options = TranscriptionOptions(locales=["en-US"], enhanced_mode=enhanced_mode)
+    options = TranscriptionOptions(enhanced_mode=enhanced_mode)
 
     # Create the request content
     request_content = TranscriptionContent(definition=options, audio=audio_file)
@@ -271,14 +285,7 @@ with open(audio_file_path, "rb") as audio_file:
     result = client.transcribe(request_content)
 
     # Print the transcription result
-    print("Transcription with enhanced mode:")
-    print(f"{result.combined_phrases[0].text}")
-
-    # Print individual phrases if available
-    if result.phrases:
-        print("\nDetailed phrases:")
-        for phrase in result.phrases:
-            print(f"  [{phrase.offset_milliseconds}ms]: {phrase.text}")
+    print(result.combined_phrases[0].text)
 ```
 
 <!-- END SNIPPET -->
@@ -296,10 +303,18 @@ from azure.ai.transcription.models import TranscriptionContent, TranscriptionOpt
 
 # Get configuration from environment variables
 endpoint = os.environ["AZURE_SPEECH_ENDPOINT"]
-api_key = os.environ["AZURE_SPEECH_API_KEY"]
+
+# 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.aio import DefaultAzureCredential
+
+    credential = DefaultAzureCredential()
 
 # Create the transcription client
-async with TranscriptionClient(endpoint=endpoint, credential=AzureKeyCredential(api_key)) as client:
+async with TranscriptionClient(endpoint=endpoint, credential=credential) as client:
     # Path to your audio file
     import pathlib
 

sdk/cognitiveservices/azure-ai-transcription/_metadata.json

@@ -1,5 +1,3 @@
 {
-  "apiVersion": "2025-10-15",
-  "service_name": "Cognitive Services",
-  "msDocService": "cognitive-services"
+  "apiVersion": "2025-10-15"
 }

sdk/cognitiveservices/azure-ai-transcription/assets.json

@@ -2,5 +2,5 @@
   "AssetsRepo": "Azure/azure-sdk-assets",
   "AssetsRepoPrefixPath": "python",
   "TagPrefix": "python/cognitiveservices/azure-ai-transcription",
-  "Tag": "python/cognitiveservices/azure-ai-transcription_5f9f60e291"
+  "Tag": "python/cognitiveservices/azure-ai-transcription_807296d8e0"
 }

sdk/cognitiveservices/azure-ai-transcription/azure/ai/transcription/_client.py

@@ -27,7 +27,7 @@ class TranscriptionClient(_TranscriptionClientOperationsMixin):
     """TranscriptionClient.
 
     :param endpoint: Supported Cognitive Services endpoints (protocol and hostname, for example:
-     `https://westus.api.cognitive.microsoft.com <https://westus.api.cognitive.microsoft.com>`_.
+     `https://westus.api.cognitive.microsoft.com <https://westus.api.cognitive.microsoft.com>`_).
      Required.
     :type endpoint: str
     :param credential: Credential used to authenticate requests to the service. Is either a key

sdk/cognitiveservices/azure-ai-transcription/azure/ai/transcription/_configuration.py

@@ -24,7 +24,7 @@ class TranscriptionClientConfiguration:  # pylint: disable=too-many-instance-att
     attributes.
 
     :param endpoint: Supported Cognitive Services endpoints (protocol and hostname, for example:
-     `https://westus.api.cognitive.microsoft.com <https://westus.api.cognitive.microsoft.com>`_.
+     `https://westus.api.cognitive.microsoft.com <https://westus.api.cognitive.microsoft.com>`_).
      Required.
     :type endpoint: str
     :param credential: Credential used to authenticate requests to the service. Is either a key

sdk/cognitiveservices/azure-ai-transcription/azure/ai/transcription/_operations/_operations.py

@@ -110,12 +110,11 @@ def transcribe(self, body: Union[_models.TranscriptionContent, JSON], **kwargs:
         _body = body.as_dict() if isinstance(body, _Model) else body
         _file_fields: list[str] = ["audio"]
         _data_fields: list[str] = ["definition"]
-        _files, _data = prepare_multipart_form_data(_body, _file_fields, _data_fields)
+        _files = prepare_multipart_form_data(_body, _file_fields, _data_fields)
 
         _request = build_transcription_transcribe_request(
             api_version=self._config.api_version,
             files=_files,
-            data=_data,
             headers=_headers,
             params=_params,
         )

sdk/cognitiveservices/azure-ai-transcription/azure/ai/transcription/_operations/_patch.py

@@ -12,7 +12,14 @@
 from typing import Any, Optional
 import json
 from azure.core.tracing.decorator import distributed_trace
-from azure.core.exceptions import map_error, HttpResponseError, ClientAuthenticationError, ResourceNotFoundError, ResourceExistsError, ResourceNotModifiedError
+from azure.core.exceptions import (
+    map_error,
+    HttpResponseError,
+    ClientAuthenticationError,
+    ResourceNotFoundError,
+    ResourceExistsError,
+    ResourceNotModifiedError,
+)
 
 from .. import models as _models
 from .._utils.model_base import _deserialize, SdkJSONEncoder
@@ -93,7 +100,9 @@ def transcribe_from_url(
         }
         _request.url = self._client.format_url(_request.url, **path_format_arguments)
 
-        pipeline_response = self._client._pipeline.run(_request, stream=False, **kwargs)  # pylint: disable=protected-access
+        pipeline_response = self._client._pipeline.run(  # pylint: disable=protected-access
+            _request, stream=False, **kwargs
+        )
         response = pipeline_response.http_response
 
         if response.status_code not in [200]: