services(stt): allow STT service to passthrough audio

CHANGELOG.md

@@ -9,6 +9,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- Added `audio_passthrough` parameter to `STTService`. If enabled it allows
+  audio frames to be pushed downstream in case other processors need them.
+
 - Added input parameter options for `PlayHTTTSService` and
   `PlayHTHttpTTSService`.
 

src/pipecat/services/ai_services.py

@@ -451,8 +451,9 @@ class WordTTSService(TTSService):
 class STTService(AIService):
     """STTService is a base class for speech-to-text services."""
 
-    def __init__(self, **kwargs):
+    def __init__(self, audio_passthrough=False, **kwargs):
         super().__init__(**kwargs)
+        self._audio_passthrough = audio_passthrough
         self._settings: Dict[str, Any] = {}
 
     @abstractmethod
@@ -490,8 +491,11 @@ class STTService(AIService):
 
         if isinstance(frame, AudioRawFrame):
             # In this service we accumulate audio internally and at the end we
-            # push a TextFrame. We don't really want to push audio frames down.
+            # push a TextFrame. We also push audio downstream in case someone
+            # else needs it.
             await self.process_audio_frame(frame)
+            if self._audio_passthrough:
+                await self.push_frame(frame, direction)
         elif isinstance(frame, STTUpdateSettingsFrame):
             await self._update_settings(frame.settings)
         else: