120 lines
4.1 KiB
Python
120 lines
4.1 KiB
Python
#
|
||
# Copyright (c) 2024–2025, Daily
|
||
#
|
||
# SPDX-License-Identifier: BSD 2-Clause License
|
||
#
|
||
|
||
import argparse
|
||
import asyncio
|
||
import os
|
||
import sys
|
||
|
||
import aiohttp
|
||
from dotenv import load_dotenv
|
||
from loguru import logger
|
||
from runner import configure_with_args
|
||
|
||
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 import CartesiaTTSService
|
||
from pipecat.services.openai 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:
|
||
parser = argparse.ArgumentParser(description="Bot Background Sound")
|
||
parser.add_argument("-i", "--input", type=str, required=True, help="Input audio file")
|
||
|
||
(room_url, token, args) = await configure_with_args(session, parser)
|
||
|
||
soundfile_mixer = SoundfileMixer(
|
||
sound_files={"office": args.input},
|
||
default_sound="office",
|
||
volume=2.0,
|
||
)
|
||
|
||
transport = DailyTransport(
|
||
room_url,
|
||
token,
|
||
"Respond bot",
|
||
DailyParams(
|
||
audio_out_enabled=True,
|
||
audio_out_mixer=soundfile_mixer,
|
||
transcription_enabled=True,
|
||
vad_enabled=True,
|
||
vad_analyzer=SileroVADAnalyzer(),
|
||
),
|
||
)
|
||
|
||
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
|
||
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_transcription(participant["id"])
|
||
# 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()])
|
||
|
||
runner = PipelineRunner()
|
||
|
||
await runner.run(task)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
asyncio.run(main())
|