transports: some local audio and tk updates

examples/foundational/01a-local-audio.py

@@ -16,7 +16,7 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.services.cartesia import CartesiaTTSService
-from pipecat.transports.local.audio import LocalAudioTransport, LocalTransportParams
+from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams
 
 load_dotenv(override=True)
 
@@ -25,7 +25,7 @@ logger.add(sys.stderr, level="DEBUG")
 
 
 async def main():
-    transport = LocalAudioTransport(LocalTransportParams(audio_out_enabled=True))
+    transport = LocalAudioTransport(LocalAudioTransportParams(audio_out_enabled=True))
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),

examples/foundational/13a-whisper-local.py

@@ -16,7 +16,7 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.whisper import WhisperSTTService
-from pipecat.transports.local.audio import LocalAudioTransport, LocalTransportParams
+from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams
 
 load_dotenv(override=True)
 
@@ -33,7 +33,7 @@ class TranscriptionLogger(FrameProcessor):
 
 
 async def main():
-    transport = LocalAudioTransport(LocalTransportParams(audio_in_enabled=True))
+    transport = LocalAudioTransport(LocalAudioTransportParams(audio_in_enabled=True))
 
     stt = WhisperSTTService()
 

examples/local-input-select-stt/bot.py

@@ -18,7 +18,7 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.whisper import Model, WhisperSTTService
-from pipecat.transports.local.audio import LocalAudioTransport, LocalTransportParams
+from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams
 
 load_dotenv(override=True)
 
@@ -36,7 +36,7 @@ class TranscriptionLogger(FrameProcessor):
 
 async def main(input_device: int, output_device: int):
     transport = LocalAudioTransport(
-        LocalTransportParams(
+        LocalAudioTransportParams(
             audio_in_enabled=True,
             audio_out_enabled=False,
             input_device_index=input_device,

src/pipecat/transports/local/audio.py

@@ -26,17 +26,18 @@ except ModuleNotFoundError as e:
     raise Exception(f"Missing module: {e}")
 
 
-class LocalTransportParams(TransportParams):
+class LocalAudioTransportParams(TransportParams):
-    input_device_index: int = 0
+    input_device_index: Optional[int] = None
-    output_device_index: int = 0
+    output_device_index: Optional[int] = None
 
 
 class LocalAudioInputTransport(BaseInputTransport):
-    _params: LocalTransportParams
+    _params: LocalAudioTransportParams
 
-    def __init__(self, py_audio: pyaudio.PyAudio, params: LocalTransportParams):
+    def __init__(self, py_audio: pyaudio.PyAudio, params: LocalAudioTransportParams):
         super().__init__(params)
         self._py_audio = py_audio
+
         self._in_stream = None
         self._sample_rate = 0
 
@@ -77,11 +78,12 @@ class LocalAudioInputTransport(BaseInputTransport):
 
 
 class LocalAudioOutputTransport(BaseOutputTransport):
-    _params: LocalTransportParams
+    _params: LocalAudioTransportParams
 
-    def __init__(self, py_audio: pyaudio.PyAudio, params: TransportParams):
+    def __init__(self, py_audio: pyaudio.PyAudio, params: LocalAudioTransportParams):
         super().__init__(params)
         self._py_audio = py_audio
+
         self._out_stream = None
         self._sample_rate = 0
 
@@ -117,7 +119,7 @@ class LocalAudioOutputTransport(BaseOutputTransport):
 
 
 class LocalAudioTransport(BaseTransport):
-    def __init__(self, params: LocalTransportParams):
+    def __init__(self, params: LocalAudioTransportParams):
         super().__init__()
         self._params = params
         self._pyaudio = pyaudio.PyAudio()

src/pipecat/transports/local/tk.py

@@ -34,8 +34,15 @@ except ModuleNotFoundError as e:
     raise Exception(f"Missing module: {e}")
 
 
+class TkTransportParams(TransportParams):
+    audio_input_device_index: Optional[int] = None
+    audio_output_device_index: Optional[int] = None
+
+
 class TkInputTransport(BaseInputTransport):
-    def __init__(self, py_audio: pyaudio.PyAudio, params: TransportParams):
+    _params: TkTransportParams
+
+    def __init__(self, py_audio: pyaudio.PyAudio, params: TkTransportParams):
         super().__init__(params)
         self._py_audio = py_audio
         self._in_stream = None
@@ -54,6 +61,7 @@ class TkInputTransport(BaseInputTransport):
             frames_per_buffer=num_frames,
             stream_callback=self._audio_in_callback,
             input=True,
+            input_device_index=self._params.audio_input_device_index,
         )
         self._in_stream.start_stream()
 
@@ -76,6 +84,8 @@ class TkInputTransport(BaseInputTransport):
 
 
 class TkOutputTransport(BaseOutputTransport):
+    _params: TkTransportParams
+
     def __init__(self, tk_root: tk.Tk, py_audio: pyaudio.PyAudio, params: TransportParams):
         super().__init__(params)
         self._py_audio = py_audio
@@ -103,6 +113,7 @@ class TkOutputTransport(BaseOutputTransport):
             channels=self._params.audio_out_channels,
             rate=self._sample_rate,
             output=True,
+            output_device_index=self._params.audio_output_device_index,
         )
         self._out_stream.start_stream()