Merge pull request #1799 from pipecat-ai/daily_audio_source

Using audio source for capturing Daily's participant audio

examples/foundational/04c-transports-daily-audio-source.py

@@ -0,0 +1,111 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+
+import aiohttp
+from daily_runner import configure
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService, Language, LiveOptions
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Respond bot",
+            DailyParams(
+                audio_in_enabled=True,
+                audio_in_passthrough=False,
+                audio_out_enabled=True,
+                audio_out_sample_rate=16000,
+                transcription_enabled=False,
+                vad_analyzer=SileroVADAnalyzer(),
+            ),
+        )
+
+        stt = DeepgramSTTService(
+            api_key=os.getenv("DEEPGRAM_API_KEY"),
+            live_options=LiveOptions(language=Language.EN),
+        )
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        )
+
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                stt,
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            params=PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await transport.capture_participant_audio(participant["id"])
+            # Kick off the conversation.
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.cancel()
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

src/pipecat/transports/services/daily.py

@@ -702,6 +702,10 @@ class DailyTransportClient(EventHandler):
 
         self._audio_renderers.setdefault(participant_id, {})[audio_source] = callback
 
+        logger.info(
+            f"Starting to capture audio from participant {participant_id} to {audio_source}"
+        )
+
         self._client.set_audio_renderer(
             participant_id,
             self._audio_data_received,
@@ -1022,7 +1026,7 @@ class DailyInputTransport(BaseInputTransport):
     async def capture_participant_audio(
         self,
         participant_id: str,
-        audio_source: str = "camera",
+        audio_source: str = "microphone",
     ):
         await self._client.capture_participant_audio(
             participant_id, self._on_participant_audio_data, audio_source