[Voice Live]Update models related to voice and conversation (#42718)

* Update models related to voice and conversation

* Update sdk/ai/azure-ai-voicelive/azure/ai/voicelive/_types.py

Co-authored-by: Copilot <[email protected]>

* use pyproject and deprecate setup.py

* update change log

---------

Co-authored-by: Xiting Zhang <[email protected]>
Co-authored-by: Copilot <[email protected]>

Author: 3 people

sdk/ai/azure-ai-voicelive/CHANGELOG.md

@@ -1,15 +1,14 @@
 # Release History
 
-## 1.0.0b1 (Unreleased)
+## 1.0.0b1 (2025-08-28)
 
 ### Features Added
 
 - Added WebSocket connection support through `connect()`.
-- Added `WebsocketConnectionOptions` to configure WebSocket connections.
 - Added `VoiceLiveConnection` for managing WebSocket connections.
+- Added models of Voice Live preview.
 - Added WebSocket-based examples in the samples directory.
 
 ### Other Changes
 
-- Added `websockets` extra in `setup.py` to install WebSocket dependencies.
 - Initial preview release.

sdk/ai/azure-ai-voicelive/apiview-properties.json

@@ -3,13 +3,21 @@
     "CrossLanguageDefinitionId": {
         "azure.ai.voicelive.models.AgentConfig": "VoiceLive.AgentConfig",
         "azure.ai.voicelive.models.Animation": "VoiceLive.Animation",
+        "azure.ai.voicelive.models.ConversationRequestItem": "VoiceLive.ConversationRequestItem",
+        "azure.ai.voicelive.models.MessageItem": "VoiceLive.MessageItem",
+        "azure.ai.voicelive.models.AssistantMessageItem": "VoiceLive.AssistantMessageItem",
         "azure.ai.voicelive.models.AudioEchoCancellation": "VoiceLive.AudioEchoCancellation",
         "azure.ai.voicelive.models.AudioInputTranscriptionSettings": "VoiceLive.AudioInputTranscriptionSettings",
         "azure.ai.voicelive.models.AudioNoiseReduction": "VoiceLive.AudioNoiseReduction",
         "azure.ai.voicelive.models.AvatarConfig": "VoiceLive.AvatarConfig",
+        "azure.ai.voicelive.models.AzureVoice": "VoiceLive.AzureVoice",
         "azure.ai.voicelive.models.AzureCustomVoice": "VoiceLive.AzureCustomVoice",
-        "azure.ai.voicelive.models.AzurePersonalVoice": "VoiceLive.AzurePersonalVoice",
         "azure.ai.voicelive.models.TurnDetection": "VoiceLive.TurnDetection",
+        "azure.ai.voicelive.models.AzureMultilingualSemanticVad": "VoiceLive.AzureMultilingualSemanticVad",
+        "azure.ai.voicelive.models.AzurePersonalVoice": "VoiceLive.AzurePersonalVoice",
+        "azure.ai.voicelive.models.EOUDetection": "VoiceLive.EOUDetection",
+        "azure.ai.voicelive.models.AzureSemanticDetection": "VoiceLive.AzureSemanticDetection",
+        "azure.ai.voicelive.models.AzureSemanticDetectionMultilingual": "VoiceLive.AzureSemanticDetectionMultilingual",
         "azure.ai.voicelive.models.AzureSemanticVad": "VoiceLive.AzureSemanticVad",
         "azure.ai.voicelive.models.AzureStandardVoice": "VoiceLive.AzureStandardVoice",
         "azure.ai.voicelive.models.ClientEvent": "VoiceLive.ClientEvent",
@@ -30,38 +38,37 @@
         "azure.ai.voicelive.models.ClientEventSessionAvatarConnect": "VoiceLive.ClientEventSessionAvatarConnect",
         "azure.ai.voicelive.models.ClientEventSessionUpdate": "VoiceLive.ClientEventSessionUpdate",
         "azure.ai.voicelive.models.ContentPart": "VoiceLive.ContentPart",
-        "azure.ai.voicelive.models.ConversationItemWithReference": "VoiceLive.ConversationItemWithReference",
-        "azure.ai.voicelive.models.ConversationItemWithReferenceContent": "VoiceLive.ConversationItemWithReference.content.anonymous",
-        "azure.ai.voicelive.models.ConversationRequestItem": "VoiceLive.ConversationRequestItem",
-        "azure.ai.voicelive.models.ConversationResponseItem": "VoiceLive.ConversationResponseItem",
+        "azure.ai.voicelive.models.FunctionCallItem": "VoiceLive.FunctionCallItem",
+        "azure.ai.voicelive.models.FunctionCallOutputItem": "VoiceLive.FunctionCallOutputItem",
         "azure.ai.voicelive.models.Tool": "VoiceLive.Tool",
         "azure.ai.voicelive.models.FunctionTool": "VoiceLive.FunctionTool",
         "azure.ai.voicelive.models.IceServer": "VoiceLive.IceServer",
         "azure.ai.voicelive.models.InputAudio": "VoiceLive.InputAudio",
+        "azure.ai.voicelive.models.UserContentPart": "VoiceLive.UserContentPart",
+        "azure.ai.voicelive.models.InputAudioContentPart": "VoiceLive.InputAudioContentPart",
+        "azure.ai.voicelive.models.InputTextContentPart": "VoiceLive.InputTextContentPart",
+        "azure.ai.voicelive.models.InputTokenDetails": "VoiceLive.InputTokenDetails",
         "azure.ai.voicelive.models.LogProbProperties": "VoiceLive.LogProbProperties",
         "azure.ai.voicelive.models.NoTurnDetection": "VoiceLive.NoTurnDetection",
-        "azure.ai.voicelive.models.RequestMessageItem": "VoiceLive.RequestMessageItem",
-        "azure.ai.voicelive.models.RequestAssistantMessageItem": "VoiceLive.RequestAssistantMessageItem",
+        "azure.ai.voicelive.models.OpenAIVoice": "VoiceLive.OpenAIVoice",
+        "azure.ai.voicelive.models.OutputTextContentPart": "VoiceLive.OutputTextContentPart",
+        "azure.ai.voicelive.models.OutputTokenDetails": "VoiceLive.OutputTokenDetails",
         "azure.ai.voicelive.models.RequestAudioContentPart": "VoiceLive.RequestAudioContentPart",
-        "azure.ai.voicelive.models.RequestFunctionCallItem": "VoiceLive.RequestFunctionCallItem",
-        "azure.ai.voicelive.models.RequestFunctionCallOutputItem": "VoiceLive.RequestFunctionCallOutputItem",
         "azure.ai.voicelive.models.RequestSession": "VoiceLive.RequestSession",
-        "azure.ai.voicelive.models.RequestSystemMessageItem": "VoiceLive.RequestSystemMessageItem",
         "azure.ai.voicelive.models.RequestTextContentPart": "VoiceLive.RequestTextContentPart",
-        "azure.ai.voicelive.models.RequestUserMessageItem": "VoiceLive.RequestUserMessageItem",
         "azure.ai.voicelive.models.Response": "VoiceLive.Response",
         "azure.ai.voicelive.models.ResponseAudioContentPart": "VoiceLive.ResponseAudioContentPart",
+        "azure.ai.voicelive.models.ResponseStatusDetails": "VoiceLive.ResponseStatusDetails",
+        "azure.ai.voicelive.models.ResponseCancelledDetails": "VoiceLive.ResponseCancelledDetails",
         "azure.ai.voicelive.models.ResponseCreateParams": "VoiceLive.ResponseCreateParams",
+        "azure.ai.voicelive.models.ResponseFailedDetails": "VoiceLive.ResponseFailedDetails",
+        "azure.ai.voicelive.models.ResponseItem": "VoiceLive.ResponseItem",
         "azure.ai.voicelive.models.ResponseFunctionCallItem": "VoiceLive.ResponseFunctionCallItem",
         "azure.ai.voicelive.models.ResponseFunctionCallOutputItem": "VoiceLive.ResponseFunctionCallOutputItem",
+        "azure.ai.voicelive.models.ResponseIncompleteDetails": "VoiceLive.ResponseIncompleteDetails",
         "azure.ai.voicelive.models.ResponseMessageItem": "VoiceLive.ResponseMessageItem",
         "azure.ai.voicelive.models.ResponseSession": "VoiceLive.ResponseSession",
-        "azure.ai.voicelive.models.ResponseStatusDetails": "VoiceLive.Response.status_details.anonymous",
-        "azure.ai.voicelive.models.ResponseStatusDetailsError": "VoiceLive.Response.status_details.error.anonymous",
         "azure.ai.voicelive.models.ResponseTextContentPart": "VoiceLive.ResponseTextContentPart",
-        "azure.ai.voicelive.models.ResponseUsage": "VoiceLive.Response.usage.anonymous",
-        "azure.ai.voicelive.models.ResponseUsageInputTokenDetails": "VoiceLive.Response.usage.input_token_details.anonymous",
-        "azure.ai.voicelive.models.ResponseUsageOutputTokenDetails": "VoiceLive.Response.usage.output_token_details.anonymous",
         "azure.ai.voicelive.models.ServerEvent": "VoiceLive.ServerEvent",
         "azure.ai.voicelive.models.ServerEventConversationItemCreated": "VoiceLive.ServerEventConversationItemCreated",
         "azure.ai.voicelive.models.ServerEventConversationItemDeleted": "VoiceLive.ServerEventConversationItemDeleted",
@@ -71,7 +78,7 @@
         "azure.ai.voicelive.models.ServerEventConversationItemRetrieved": "VoiceLive.ServerEventConversationItemRetrieved",
         "azure.ai.voicelive.models.ServerEventConversationItemTruncated": "VoiceLive.ServerEventConversationItemTruncated",
         "azure.ai.voicelive.models.ServerEventError": "VoiceLive.ServerEventError",
-        "azure.ai.voicelive.models.ServerEventErrorError": "VoiceLive.ServerEventError.error.anonymous",
+        "azure.ai.voicelive.models.ServerEventErrorDetails": "VoiceLive.ServerEventError.error.anonymous",
         "azure.ai.voicelive.models.ServerEventInputAudioBufferCleared": "VoiceLive.ServerEventInputAudioBufferCleared",
         "azure.ai.voicelive.models.ServerEventInputAudioBufferCommitted": "VoiceLive.ServerEventInputAudioBufferCommitted",
         "azure.ai.voicelive.models.ServerEventInputAudioBufferSpeechStarted": "VoiceLive.ServerEventInputAudioBufferSpeechStarted",
@@ -92,18 +99,22 @@
         "azure.ai.voicelive.models.ServerEventSessionCreated": "VoiceLive.ServerEventSessionCreated",
         "azure.ai.voicelive.models.ServerEventSessionUpdated": "VoiceLive.ServerEventSessionUpdated",
         "azure.ai.voicelive.models.ServerVad": "VoiceLive.ServerVad",
+        "azure.ai.voicelive.models.SystemMessageItem": "VoiceLive.SystemMessageItem",
         "azure.ai.voicelive.models.ToolChoiceObject": "VoiceLive.ToolChoiceObject",
         "azure.ai.voicelive.models.ToolChoiceFunctionObject": "VoiceLive.ToolChoiceFunctionObject",
         "azure.ai.voicelive.models.ToolChoiceFunctionObjectFunction": "VoiceLive.ToolChoiceFunctionObject.function.anonymous",
+        "azure.ai.voicelive.models.Usage": "VoiceLive.Usage",
+        "azure.ai.voicelive.models.UserMessageItem": "VoiceLive.UserMessageItem",
         "azure.ai.voicelive.models.VideoCrop": "VoiceLive.VideoCrop",
         "azure.ai.voicelive.models.VideoParams": "VoiceLive.VideoParams",
         "azure.ai.voicelive.models.VideoResolution": "VoiceLive.VideoResolution",
         "azure.ai.voicelive.models.VoiceLiveErrorDetails": "VoiceLive.VoiceLiveErrorDetails",
         "azure.ai.voicelive.models.ServerEventType": "VoiceLive.ServerEventType",
-        "azure.ai.voicelive.models.ContentPartType": "VoiceLive.ContentPartType",
         "azure.ai.voicelive.models.ItemType": "VoiceLive.ItemType",
-        "azure.ai.voicelive.models.ItemStatus": "VoiceLive.ItemStatus",
+        "azure.ai.voicelive.models.ResponseItemStatus": "VoiceLive.ResponseItemStatus",
         "azure.ai.voicelive.models.MessageRole": "VoiceLive.MessageRole",
+        "azure.ai.voicelive.models.ContentPartType": "VoiceLive.ContentPartType",
+        "azure.ai.voicelive.models.ResponseStatus": "VoiceLive.ResponseStatus",
         "azure.ai.voicelive.models.OAIVoice": "VoiceLive.OAIVoice",
         "azure.ai.voicelive.models.Phi4mmVoice": "VoiceLive.Phi4mmVoice",
         "azure.ai.voicelive.models.Modality": "VoiceLive.Modality",
@@ -112,6 +123,7 @@
         "azure.ai.voicelive.models.AudioTimestampType": "VoiceLive.AudioTimestampType",
         "azure.ai.voicelive.models.ToolType": "VoiceLive.ToolType",
         "azure.ai.voicelive.models.ToolChoiceLiteral": "VoiceLive.ToolChoiceLiteral",
-        "azure.ai.voicelive.models.ClientEventType": "VoiceLive.ClientEventType"
+        "azure.ai.voicelive.models.ClientEventType": "VoiceLive.ClientEventType",
+        "azure.ai.voicelive.models.ItemParamStatus": "VoiceLive.ItemParamStatus"
     }
 }

sdk/ai/azure-ai-voicelive/azure/ai/voicelive/_patch.py

@@ -12,6 +12,7 @@
 import logging
 from contextlib import AbstractContextManager
 from urllib.parse import parse_qs, urlencode, urlparse, urlunparse
+
 try:  # Python 3.11+
     from typing import NotRequired  # type: ignore[attr-defined]
 except Exception:  # Python <=3.10
@@ -41,9 +42,11 @@
     try:
         from websockets.typing import Subprotocol as WSSubprotocol  # runtime if available
     except Exception:
+
         class WSSubprotocol(str):  # fallback, keeps runtime simple
             pass
 
+
 __all__: List[str] = [
     "connect",
     "WebsocketConnectionOptions",
@@ -61,6 +64,7 @@ class WSSubprotocol(str):  # fallback, keeps runtime simple
 
 log = logging.getLogger(__name__)
 
+
 def _json_default(o: Any) -> Any:
     """
     Fallback JSON serializer for generated SDK models and other custom objects.
@@ -89,13 +93,14 @@ def _json_default(o: Any) -> Any:
         return {k: v for k, v in vars(o).items() if not k.startswith("_")}
     raise TypeError(f"{type(o).__name__} is not JSON serializable")
 
+
 class WebsocketConnectionOptions(TypedDict, total=False):
     """
     Advanced WebSocket connection options for the synchronous VoiceLive API.
 
     These options are passed directly to :func:`websockets.sync.client.connect`
-    and control low-level WebSocket behavior.  
-    All keys are optional — if omitted, the `websockets` library's defaults apply.  
+    and control low-level WebSocket behavior.
+    All keys are optional — if omitted, the `websockets` library's defaults apply.
     Unsupported or unknown keys are ignored.
 
     :keyword extensions: WebSocket extensions to negotiate with the server.
@@ -649,7 +654,7 @@ def __enter__(self) -> VoiceLiveConnection:
     def __exit__(self, exc_type, exc, exc_tb) -> None:
         """
         Close the connection when exiting the context.
-        
+
         :param exc_type: Exception type if an error occurred.
         :type exc_type: type | None
         :param exc: Exception instance if an error occurred.
@@ -664,7 +669,7 @@ def __exit__(self, exc_type, exc, exc_tb) -> None:
 
     def _get_auth_headers(self) -> Dict[str, str]:
         """Get authentication headers for WebSocket connection.
-        
+
         :return: A dictionary containing authentication headers.
         :rtype: dict[str, str]
         """
@@ -740,7 +745,7 @@ def connect(
     :paramtype connection_options: ~azure.ai.voicelive.WebsocketConnectionOptions or None
     :return: A context manager that yields a connected :class:`~azure.ai.voicelive.VoiceLiveConnection`.
     :rtype: contextlib.AbstractContextManager[~azure.ai.voicelive.VoiceLiveConnection]
-    
+
     .. note::
         Additional keyword arguments can be passed and will be forwarded to the underlying connection.
     """

sdk/ai/azure-ai-voicelive/azure/ai/voicelive/_types.py

@@ -6,18 +6,9 @@
 # Changes may cause incorrect behavior and will be lost if the code is regenerated.
 # --------------------------------------------------------------------------
 
-from typing import TYPE_CHECKING, Literal, Union
+from typing import TYPE_CHECKING, Union
 
 if TYPE_CHECKING:
     from . import models as _models
-Voice = Union[
-    str,
-    "_models.OAIVoice",
-    "_models.AzureStandardVoice",
-    "_models.AzureCustomVoice",
-    "_models.AzurePersonalVoice",
-    str,
-    "_models.Phi4mmVoice",
-]
+Voice = Union[str, "_models.OAIVoice", "_models.OpenAIVoice", "_models.AzureVoice", "_models.Phi4mmVoice"]
 ToolChoice = Union[str, "_models.ToolChoiceLiteral", "_models.ToolChoiceObject"]
-ReasoningEffort = Literal["minimal", "low", "medium", "high"]

sdk/ai/azure-ai-voicelive/azure/ai/voicelive/aio/_patch.py

@@ -11,6 +11,7 @@
 import logging
 from contextlib import AbstractAsyncContextManager
 from urllib.parse import urlparse, urlunparse, urlencode, parse_qs
+
 # pylint: disable=ungrouped-imports
 try:  # Python 3.11+
     from typing import NotRequired  # type: ignore[attr-defined]
@@ -77,6 +78,7 @@ def _json_default(o: Any) -> Any:
         return {k: v for k, v in vars(o).items() if not k.startswith("_")}
     raise TypeError(f"{type(o).__name__} is not JSON serializable")
 
+
 class SessionResource:
     """Resource for session management."""
 
@@ -493,9 +495,7 @@ async def send(self, event: Union[Mapping[str, Any], ClientEvent]) -> None:
                 payload = json.dumps(event, default=_json_default)
 
             # Ensure we pass a str to send_str
-            data: str = (
-                payload if isinstance(payload, str) else json.dumps(payload, default=_json_default)
-            )
+            data: str = payload if isinstance(payload, str) else json.dumps(payload, default=_json_default)
 
             await self._connection.send_str(data)
         except (TypeError, ValueError, aiohttp.ClientError, RuntimeError) as e:
@@ -645,9 +645,7 @@ async def __aenter__(self) -> VoiceLiveConnection:
 
             session = aiohttp.ClientSession()
             try:
-                connection_obj = await session.ws_connect(
-                    str(url), headers=headers, **self.__connection_options
-                )
+                connection_obj = await session.ws_connect(str(url), headers=headers, **self.__connection_options)
                 self.__connection = VoiceLiveConnection(session, connection_obj)
                 return self.__connection
             except aiohttp.ClientError as e:
@@ -746,7 +744,7 @@ def connect(
     :paramtype type connection_options: ~azure.ai.voicelive.aio.WebsocketConnectionOptions
     :return: An async context manager yielding a connected :class:`~azure.ai.voicelive.aio.VoiceLiveConnection`.
     :rtype: collections.abc.AsyncContextManager[~azure.ai.voicelive.aio.VoiceLiveConnection]
-    
+
     .. note::
         Additional keyword arguments can be passed and will be forwarded to the underlying connection.
     """