138 lines
4.5 KiB
Python
138 lines
4.5 KiB
Python
#
|
||
# Copyright (c) 2024–2025, Daily
|
||
#
|
||
# SPDX-License-Identifier: BSD 2-Clause License
|
||
#
|
||
|
||
"""Usage
|
||
-----
|
||
Set the path to your background audio file using the `INPUT_AUDIO_PATH` environment variable, then run the bot using:
|
||
|
||
INPUT_AUDIO_PATH=path/to/your_audio.mp3 python 23-bot-background-sound.py
|
||
|
||
Example:
|
||
INPUT_AUDIO_PATH=my_audio.mp3 python 23-bot-background-sound.py
|
||
"""
|
||
|
||
import argparse
|
||
import asyncio
|
||
import os
|
||
|
||
from dotenv import load_dotenv
|
||
from loguru import logger
|
||
|
||
from pipecat.audio.mixers.soundfile_mixer import SoundfileMixer
|
||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||
from pipecat.frames.frames import MixerEnableFrame, MixerUpdateSettingsFrame
|
||
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
|
||
from pipecat.services.openai.llm import OpenAILLMService
|
||
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)
|
||
|
||
audio_path = os.getenv("INPUT_AUDIO_PATH")
|
||
if not audio_path:
|
||
raise ValueError("No INPUT_AUDIO_PATH specified in environment variables")
|
||
|
||
|
||
async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespace):
|
||
logger.info(f"Starting bot")
|
||
|
||
soundfile_mixer = SoundfileMixer(
|
||
sound_files={"office": audio_path},
|
||
default_sound="office",
|
||
volume=2.0,
|
||
)
|
||
|
||
transport = SmallWebRTCTransport(
|
||
webrtc_connection=webrtc_connection,
|
||
params=TransportParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
audio_out_mixer=soundfile_mixer,
|
||
vad_analyzer=SileroVADAnalyzer(),
|
||
),
|
||
)
|
||
|
||
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"))
|
||
|
||
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, # STT service
|
||
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_client_connected")
|
||
async def on_client_connected(transport, client):
|
||
logger.info(f"Client connected: {client}")
|
||
# Show how to use mixer control frames.
|
||
await asyncio.sleep(10.0)
|
||
await task.queue_frame(MixerUpdateSettingsFrame({"volume": 0.5}))
|
||
await asyncio.sleep(5.0)
|
||
await task.queue_frame(MixerEnableFrame(False))
|
||
await asyncio.sleep(5.0)
|
||
await task.queue_frame(MixerEnableFrame(True))
|
||
await asyncio.sleep(5.0)
|
||
# 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_client_disconnected")
|
||
async def on_client_disconnected(transport, client):
|
||
logger.info(f"Client disconnected")
|
||
|
||
@transport.event_handler("on_client_closed")
|
||
async def on_client_closed(transport, client):
|
||
logger.info(f"Client closed connection")
|
||
await task.cancel()
|
||
|
||
runner = PipelineRunner(handle_sigint=False)
|
||
|
||
await runner.run(task)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
from run import main
|
||
|
||
main()
|