Merge pull request #2995 from pipecat-ai/mb/fix-stt-mute-filter-stt-muting

fix: STTMuteFilter no longer sends STTMuteFrame

CHANGELOG.md

@@ -66,6 +66,13 @@ reason")`.
 
 ### Changed
 
+- `STTMuteFilter` no longer sends `STTMuteFrame` to the STT service. The filter
+  now blocks frames locally without instructing the STT service to stop
+  processing audio. This prevents inactivity-related errors (such as 409 errors
+  from Google STT) while maintaining the same muting behavior at the application
+  level. Important: The STTMuteFilter should be placed _after_ the STT service
+  itself.
+
 - Bumped the `fastapi` dependency's upperbound to `<0.122.0`.
 
 - Updated the default model for `GoogleVertexLLMService` to `gemini-2.5-flash`.

src/pipecat/processors/filters/stt_mute_filter.py

@@ -118,24 +118,16 @@ class STTMuteFilter(FrameProcessor):
         self._first_speech_handled = False
         self._bot_is_speaking = False
         self._function_call_in_progress = False
-        self._is_muted = False  # Initialize as unmuted, will set state on StartFrame if needed
+        self._is_muted = False
-
-    @property
-    def is_muted(self) -> bool:
-        """Check if STT is currently muted.
-
-        Returns:
-            True if STT is currently muted and audio frames are being suppressed.
-        """
-        return self._is_muted
 
     async def _handle_mute_state(self, should_mute: bool):
         """Handle STT muting and interruption control state changes."""
-        if should_mute != self.is_muted:
+        if should_mute != self._is_muted:
             logger.debug(f"STTMuteFilter {'muting' if should_mute else 'unmuting'}")
             self._is_muted = should_mute
-            await self.push_frame(STTMuteFrame(mute=should_mute), FrameDirection.UPSTREAM)
+            # Note: We don't send STTMuteFrame to the STT service itself.
-            await self.push_frame(STTMuteFrame(mute=should_mute), FrameDirection.DOWNSTREAM)
+            # The filter blocks frames locally, but the STT service continues
+            # processing audio to keep streaming connections alive (e.g., Google STT).
 
     async def _should_mute(self) -> bool:
         """Determine if STT should be muted based on current state and strategies."""
@@ -215,7 +207,7 @@ class STTMuteFilter(FrameProcessor):
             ),
         ):
             # Only pass VAD-related frames when not muted
-            if not self.is_muted:
+            if not self._is_muted:
                 await self.push_frame(frame, direction)
             else:
                 logger.trace(f"{frame.__class__.__name__} suppressed - STT currently muted")
@@ -224,5 +216,5 @@ class STTMuteFilter(FrameProcessor):
             await self.push_frame(frame, direction)
 
         # Finally handle mute state change if needed
-        if should_mute is not None and should_mute != self.is_muted:
+        if should_mute is not None and should_mute != self._is_muted:
             await self._handle_mute_state(should_mute)

tests/test_stt_mute_filter.py

@@ -13,7 +13,6 @@ from pipecat.frames.frames import (
     FunctionCallResultFrame,
     InputAudioRawFrame,
     InterimTranscriptionFrame,
-    STTMuteFrame,
     TranscriptionFrame,
     UserStartedSpeakingFrame,
     UserStoppedSpeakingFrame,
@@ -49,9 +48,7 @@ class TestSTTMuteFilter(unittest.IsolatedAsyncioTestCase):
 
         expected_returned_frames = [
             BotStartedSpeakingFrame,
-            STTMuteFrame,  # mute=True
             BotStoppedSpeakingFrame,
-            STTMuteFrame,  # mute=False
             BotStartedSpeakingFrame,
             VADUserStartedSpeakingFrame,  # Now passes through
             UserStartedSpeakingFrame,  # Now passes through
@@ -98,18 +95,14 @@ class TestSTTMuteFilter(unittest.IsolatedAsyncioTestCase):
 
         expected_returned_frames = [
             BotStartedSpeakingFrame,
-            STTMuteFrame,  # mute=True
             BotStoppedSpeakingFrame,
-            STTMuteFrame,  # mute=False
             VADUserStartedSpeakingFrame,
             UserStartedSpeakingFrame,
             InputAudioRawFrame,
             VADUserStoppedSpeakingFrame,
             UserStoppedSpeakingFrame,
             BotStartedSpeakingFrame,
-            STTMuteFrame,  # mute=True
             BotStoppedSpeakingFrame,
-            STTMuteFrame,  # mute=False
         ]
 
         await run_test(
@@ -144,9 +137,7 @@ class TestSTTMuteFilter(unittest.IsolatedAsyncioTestCase):
 
         expected_returned_frames = [
             BotStartedSpeakingFrame,
-            STTMuteFrame,  # mute=True
             BotStoppedSpeakingFrame,
-            STTMuteFrame,  # mute=False
             InterimTranscriptionFrame,  # Only passes through after bot stops speaking
             TranscriptionFrame,  # Only passes through after bot stops speaking
         ]
@@ -193,9 +184,7 @@ class TestSTTMuteFilter(unittest.IsolatedAsyncioTestCase):
     #         VADUserStoppedSpeakingFrame,
     #         UserStoppedSpeakingFrame,
     #         FunctionCallInProgressFrame,
-    #         STTMuteFrame,  # mute=True
     #         FunctionCallResultFrame,
-    #         STTMuteFrame,  # mute=False
     #         VADUserStartedSpeakingFrame,
     #         UserStartedSpeakingFrame,
     #         VADUserStoppedSpeakingFrame,
@@ -245,10 +234,8 @@ class TestSTTMuteFilter(unittest.IsolatedAsyncioTestCase):
         ]
 
         expected_returned_frames = [
-            STTMuteFrame,  # mute=True after first speech
             BotStartedSpeakingFrame,
             BotStoppedSpeakingFrame,
-            STTMuteFrame,  # mute=False after first speech
             VADUserStartedSpeakingFrame,
             UserStartedSpeakingFrame,
             InputAudioRawFrame,
@@ -320,9 +307,7 @@ class TestSTTMuteFilter(unittest.IsolatedAsyncioTestCase):
             VADUserStoppedSpeakingFrame,
             UserStoppedSpeakingFrame,
             BotStartedSpeakingFrame,
-            STTMuteFrame,  # mute=True
             BotStoppedSpeakingFrame,
-            STTMuteFrame,  # mute=False
             VADUserStartedSpeakingFrame,
             UserStartedSpeakingFrame,
             InputAudioRawFrame,