Merge 'feat/support_audio' into 'feat/vlm_for_e2e'

feat: add audio

See merge request: !428

Author: wgzesg-bd

volcenginesdkarkruntime/types/chat/chat_completion_audio.py

@@ -0,0 +1,22 @@
+from ..._models import BaseModel
+
+__all__ = ["ChatCompletionAudio"]
+
+
+class ChatCompletionAudio(BaseModel):
+    id: str
+    """Unique identifier for this audio response."""
+
+    data: str
+    """
+    Base64 encoded audio bytes generated by the model.
+    """
+
+    expires_at: int
+    """
+    The Unix timestamp (in seconds) for when this audio response will no longer be
+    accessible on the server for use in multi-turn conversations.
+    """
+
+    transcript: str
+    """Transcript of the audio generated by the model."""

volcenginesdkarkruntime/types/chat/chat_completion_message.py

@@ -3,6 +3,7 @@
 
 from ..._models import BaseModel
 from .chat_completion_message_tool_call import ChatCompletionMessageToolCall
+from .chat_completion_audio import ChatCompletionAudio
 
 __all__ = ["ChatCompletionMessage", "FunctionCall"]
 
@@ -36,3 +37,6 @@ class ChatCompletionMessage(BaseModel):
 
     tool_calls: Optional[List[ChatCompletionMessageToolCall]] = None
     """The tool calls generated by the model, such as function calls."""
+
+    audio: Optional[ChatCompletionAudio] = None
+    """Audio response from the model."""