Merge pull request #4497 from pipecat-ai/aleix/fix-tts-context-id-fallback

Fall back to _turn_context_id in get_active_audio_context_id

changelog/4497.fixed.md

@@ -0,0 +1 @@
+- Fixed dropped audio in streaming TTS services whose wire protocol doesn't echo `context_id` back on incoming audio (Sarvam, Smallest, Soniox, Inworld, and others). Previously, audio that arrived between contexts or at the very start of a turn was tagged with `context_id=None` and silently dropped with an "unable to append audio to context: no context ID provided" debug log. `TTSService.get_active_audio_context_id()` now falls back to the synthesis-side `_turn_context_id` when the playback cursor isn't set yet.

examples/function-calling/function-calling-qwen.py

@@ -71,8 +71,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     llm = QwenLLMService(
         api_key=os.environ["QWEN_API_KEY"],
-        model="qwen2.5-72b-instruct",
         settings=QwenLLMService.Settings(
+            model="qwen2.5-72b-instruct",
             system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )

src/pipecat/services/tts_service.py

@@ -1283,10 +1283,17 @@ class TTSService(AIService):
     def get_active_audio_context_id(self) -> str | None:
         """Get the active audio context ID.
 
+        Returns the playback cursor when set (during active playback), falling
+        back to the current turn's synthesis context_id. The fallback covers
+        the gap between contexts and the start of a turn before the playback
+        task has popped the just-created context off the serialization queue —
+        important for services whose wire protocol does not echo context_id
+        back on incoming audio.
+
         Returns:
-            The active context ID, or None if no context is active.
+            The active context ID, or None if neither cursor is set.
         """
-        return self._playing_context_id
+        return self._playing_context_id or self._turn_context_id
 
     async def remove_active_audio_context(self):
         """Remove the active audio context."""