transports: deprecate TransportParams.vad_enabled

CHANGELOG.md

@@ -27,6 +27,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Deprecated
 
+- `TransportParams.vad_enabled` parameter is now deprecated, use
+  `TransportParams.audio_in_enabled` and `TransportParams.vad_analyzer` instead.
+
 - `TransportParams.vad_audio_passthrough` parameter is now deprecated, use
   `TransportParams.audio_in_passthrough` instead.
 

src/pipecat/transports/base_input.py

@@ -55,6 +55,17 @@ class BaseInputTransport(FrameProcessor):
         # if passthrough is enabled.
         self._audio_task = None
 
+        if self._params.vad_enabled:
+            import warnings
+
+            with warnings.catch_warnings():
+                warnings.simplefilter("always")
+                warnings.warn(
+                    "Parameter 'vad_enabled' is deprecated, use 'audio_in_enabled' and 'vad_analyzer' instead.",
+                    DeprecationWarning,
+                )
+            self._params.audio_in_enabled = True
+
         if self._params.vad_audio_passthrough:
             import warnings
 
@@ -89,7 +100,7 @@ class BaseInputTransport(FrameProcessor):
         self._sample_rate = self._params.audio_in_sample_rate or frame.audio_in_sample_rate
 
         # Configure VAD analyzer.
-        if self._params.vad_enabled and self._params.vad_analyzer:
+        if self._params.vad_analyzer:
             self._params.vad_analyzer.set_sample_rate(self._sample_rate)
         # Configure End of turn analyzer.
         if self._params.turn_analyzer:
@@ -99,13 +110,13 @@ class BaseInputTransport(FrameProcessor):
         if self._params.audio_in_filter:
             await self._params.audio_in_filter.start(self._sample_rate)
         # Create audio input queue and task if needed.
-        if not self._audio_task and (self._params.audio_in_enabled or self._params.vad_enabled):
+        if not self._audio_task and self._params.audio_in_enabled:
             self._audio_in_queue = asyncio.Queue()
             self._audio_task = self.create_task(self._audio_task_handler())
 
     async def stop(self, frame: EndFrame):
         # Cancel and wait for the audio input task to finish.
-        if self._audio_task and (self._params.audio_in_enabled or self._params.vad_enabled):
+        if self._audio_task and self._params.audio_in_enabled:
             await self.cancel_task(self._audio_task)
             self._audio_task = None
         # Stop audio filter.
@@ -114,12 +125,12 @@ class BaseInputTransport(FrameProcessor):
 
     async def cancel(self, frame: CancelFrame):
         # Cancel and wait for the audio input task to finish.
-        if self._audio_task and (self._params.audio_in_enabled or self._params.vad_enabled):
+        if self._audio_task and self._params.audio_in_enabled:
             await self.cancel_task(self._audio_task)
             self._audio_task = None
 
     async def push_audio_frame(self, frame: InputAudioRawFrame):
-        if self._params.audio_in_enabled or self._params.vad_enabled:
+        if self._params.audio_in_enabled:
             await self._audio_in_queue.put(frame)
 
     #
@@ -265,7 +276,7 @@ class BaseInputTransport(FrameProcessor):
             # Check VAD and push event if necessary. We just care about
             # changes from QUIET to SPEAKING and vice versa.
             previous_vad_state = vad_state
-            if self._params.vad_enabled:
+            if self._params.vad_analyzer:
                 vad_state = await self._handle_vad(frame, vad_state)
 
             if self._params.turn_analyzer:

src/pipecat/transports/network/small_webrtc.py

@@ -389,9 +389,7 @@ class SmallWebRTCInputTransport(BaseInputTransport):
         await super().start(frame)
         await self._client.setup(self._params, frame)
         await self._client.connect()
-        if not self._receive_audio_task and (
+        if not self._receive_audio_task and self._params.audio_in_enabled:
-            self._params.audio_in_enabled or self._params.vad_enabled
-        ):
             self._receive_audio_task = self.create_task(self._receive_audio())
         if not self._receive_video_task and self._params.camera_in_enabled:
             self._receive_video_task = self.create_task(self._receive_video())

src/pipecat/transports/services/daily.py

@@ -399,7 +399,7 @@ class DailyTransportClient(EventHandler):
                 non_blocking=True,
             )
 
-        if (self._params.audio_in_enabled or self._params.vad_enabled) and not self._speaker:
+        if self._params.audio_in_enabled and not self._speaker:
             self._speaker = Daily.create_speaker_device(
                 self._speaker_name(),
                 sample_rate=self._in_sample_rate,
@@ -846,7 +846,7 @@ class DailyInputTransport(BaseInputTransport):
     def start_audio_in_streaming(self):
         # Create audio task. It reads audio frames from Daily and push them
         # internally for VAD processing.
-        if not self._audio_in_task and (self._params.audio_in_enabled or self._params.vad_enabled):
+        if not self._audio_in_task and self._params.audio_in_enabled:
             logger.debug(f"Start receiving audio")
             self._audio_in_task = self.create_task(self._audio_in_task_handler())
 
@@ -863,9 +863,6 @@ class DailyInputTransport(BaseInputTransport):
         await self._client.setup(frame)
         # Join the room.
         await self._client.join()
-        # Inialize WebRTC VAD if needed.
-        if self._params.vad_enabled and not self._params.vad_analyzer:
-            self._vad_analyzer = WebRTCVADAnalyzer(sample_rate=self.sample_rate)
         if self._params.audio_in_stream_on_start:
             self.start_audio_in_streaming()
 
@@ -875,7 +872,7 @@ class DailyInputTransport(BaseInputTransport):
         # Leave the room.
         await self._client.leave()
         # Stop audio thread.
-        if self._audio_in_task and (self._params.audio_in_enabled or self._params.vad_enabled):
+        if self._audio_in_task and self._params.audio_in_enabled:
             await self.cancel_task(self._audio_in_task)
             self._audio_in_task = None
 
@@ -885,7 +882,7 @@ class DailyInputTransport(BaseInputTransport):
         # Leave the room.
         await self._client.leave()
         # Stop audio thread.
-        if self._audio_in_task and (self._params.audio_in_enabled or self._params.vad_enabled):
+        if self._audio_in_task and self._params.audio_in_enabled:
             await self.cancel_task(self._audio_in_task)
             self._audio_in_task = None
 

src/pipecat/transports/services/livekit.py

@@ -368,7 +368,7 @@ class LiveKitInputTransport(BaseInputTransport):
         await super().start(frame)
         await self._client.setup(frame)
         await self._client.connect()
-        if not self._audio_in_task and (self._params.audio_in_enabled or self._params.vad_enabled):
+        if not self._audio_in_task and self._params.audio_in_enabled:
             self._audio_in_task = self.create_task(self._audio_in_task_handler())
         logger.info("LiveKitInputTransport started")
 
@@ -382,7 +382,7 @@ class LiveKitInputTransport(BaseInputTransport):
     async def cancel(self, frame: CancelFrame):
         await super().cancel(frame)
         await self._client.disconnect()
-        if self._audio_in_task and (self._params.audio_in_enabled or self._params.vad_enabled):
+        if self._audio_in_task and self._params.audio_in_enabled:
             await self.cancel_task(self._audio_in_task)
 
     async def cleanup(self):