feat: implement OpenAI-compatible Realtime API with authentication and management features

- Added support for public Realtime API, including new routes for managing API keys and handling WebRTC connections.
- Introduced RealtimeApiKey model and associated CRUD operations for admin management of API keys.
- Implemented authentication mechanisms for API keys and client secrets.
- Enhanced environment configuration with new secrets for Realtime API.
- Created OpenAIRealtime session management and event processing for real-time interactions.
- Updated schemas and settings to accommodate new features and ensure compatibility with existing systems.

backend/services/pipecat/qwen_audio_realtime.py

@@ -41,13 +41,14 @@ from services.pipecat.realtime_tools import (
     RealtimeToolDispatcher,
     RealtimeToolSession,
 )
+from services.realtime.protocol import RealtimeProviderControlFrame
 
 
 DEFAULT_QWEN_AUDIO_REALTIME_MODEL = "qwen-audio-3.0-realtime-flash"
 DEFAULT_QWEN_AUDIO_REALTIME_VOICE = "longanqian"
 QWEN_INPUT_SAMPLE_RATE = 16_000
 QWEN_OUTPUT_SAMPLE_RATE = 24_000
-SUPPORTED_TURN_DETECTION_MODES = frozenset({"server_vad", "smart_turn"})
+SUPPORTED_TURN_DETECTION_MODES = frozenset({"none", "server_vad", "smart_turn"})
 
 ExtraEventHandler = Callable[[dict[str, Any]], Awaitable[None] | None]
 SpeechStartedHandler = Callable[[], Awaitable[None]]
@@ -161,6 +162,15 @@ class QwenAudioRealtimeService(AIService):
     async def process_frame(self, frame: Frame, direction: FrameDirection) -> None:
         await super().process_frame(frame, direction)
 
+        if isinstance(frame, RealtimeProviderControlFrame):
+            if frame.action == "commit_audio":
+                await self.commit_audio_buffer()
+            elif frame.action == "clear_audio":
+                await self.clear_audio_buffer()
+            else:
+                await self.request_response()
+            return
+
         if isinstance(frame, InputAudioRawFrame):
             if (
                 frame.sample_rate != self._input_sample_rate
@@ -234,6 +244,20 @@ class QwenAudioRealtimeService(AIService):
             )
         await self._send_event({"type": "response.create"})
 
+    async def commit_audio_buffer(self) -> None:
+        await self._send_event({"type": "input_audio_buffer.commit"})
+
+    async def clear_audio_buffer(self) -> None:
+        await self._send_event({"type": "input_audio_buffer.clear"})
+
+    async def update_turn_detection(self, config: dict[str, Any] | None) -> None:
+        """Apply OpenAI PTT before provider startup; reject unsafe live changes."""
+
+        mode = "none" if config is None else "server_vad"
+        if self._session_ready.is_set():
+            raise ValueError("Qwen Realtime 不支持会话建立后切换轮次检测")
+        self._turn_detection_mode = mode
+
     async def wait_for_response_boundary(self) -> None:
         """Wait until Qwen has finished or cancelled the current response."""
         await self._response_done.wait()
@@ -355,7 +379,9 @@ class QwenAudioRealtimeService(AIService):
             "tool_choice": "auto",
         }
 
-    def _turn_detection_config(self) -> dict[str, Any]:
+    def _turn_detection_config(self) -> dict[str, Any] | None:
+        if self._turn_detection_mode == "none":
+            return None
         if self._turn_detection_mode == "smart_turn":
             return {"type": "smart_turn"}
         return {