Updating foundation examples to use SmallWebRTCTransport and pipecat-ai-small-webrtc-prebuilt (#1534)

Co-authored-by: Filipi Fuchter <filipi@daily.co>

examples/foundational/11-sound-effects.py

@@ -4,21 +4,18 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 import wave
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import (
     Frame,
     LLMFullResponseEndFrame,
     OutputAudioRawFrame,
+    TTSSpeakFrame,
 )
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -30,14 +27,14 @@ from pipecat.processors.aggregators.openai_llm_context import (
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.processors.logger import FrameLogger
 from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
 
 sounds = {}
 sound_files = ["ding1.wav", "ding2.wav"]
@@ -80,70 +77,83 @@ class InboundSoundEffectWrapper(FrameProcessor):
             await self.push_frame(frame, direction)
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        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. Respond to what the user said in a creative and helpful way.",
-            },
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    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. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+    out_sound = OutboundSoundEffectWrapper()
+    in_sound = InboundSoundEffectWrapper()
+    fl = FrameLogger("LLM Out")
+    fl2 = FrameLogger("Transcription In")
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            context_aggregator.user(),
+            in_sound,
+            fl2,
+            llm,
+            fl,
+            tts,
+            out_sound,
+            transport.output(),
+            context_aggregator.assistant(),
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
-        out_sound = OutboundSoundEffectWrapper()
-        in_sound = InboundSoundEffectWrapper()
-        fl = FrameLogger("LLM Out")
-        fl2 = FrameLogger("Transcription In")
+    task = PipelineTask(pipeline)
 
-        pipeline = Pipeline(
-            [
-                transport.input(),
-                context_aggregator.user(),
-                in_sound,
-                fl2,
-                llm,
-                fl,
-                tts,
-                out_sound,
-                transport.output(),
-                context_aggregator.assistant(),
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        await task.queue_frame(TTSSpeakFrame("Hi, I'm listening!"))
+        await transport.send_audio(sounds["ding1.wav"])
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            await tts.say("Hi, I'm listening!")
-            await transport.send_audio(sounds["ding1.wav"])
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        runner = PipelineRunner()
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        task = PipelineTask(pipeline)
+    runner = PipelineRunner(handle_sigint=False)
 
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()