142 lines
4.9 KiB
Python
142 lines
4.9 KiB
Python
#
|
|
# Copyright (c) 2024, Daily
|
|
#
|
|
# SPDX-License-Identifier: BSD 2-Clause License
|
|
#
|
|
|
|
import asyncio
|
|
import os
|
|
import sys
|
|
|
|
import aiohttp
|
|
import datetime
|
|
import wave
|
|
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 EndFrame, LLMMessagesFrame
|
|
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.processors.audio.audio_buffer_processor import AudioBufferProcessor
|
|
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
|
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 save_audio(audiobuffer):
|
|
if audiobuffer.has_audio():
|
|
merged_audio = audiobuffer.merge_audio_buffers()
|
|
filename = f"conversation_recording{datetime.datetime.now().strftime('%Y%m%d_%H%M%S')}.wav"
|
|
with wave.open(filename, "wb") as wf:
|
|
wf.setnchannels(2)
|
|
wf.setsampwidth(2)
|
|
wf.setframerate(audiobuffer._sample_rate)
|
|
wf.writeframes(merged_audio)
|
|
print(f"Merged audio saved to {filename}")
|
|
else:
|
|
print("No audio data to save")
|
|
|
|
|
|
async def main():
|
|
async with aiohttp.ClientSession() as session:
|
|
(room_url, token) = await configure(session)
|
|
|
|
transport = DailyTransport(
|
|
room_url,
|
|
token,
|
|
"Chatbot",
|
|
DailyParams(
|
|
audio_out_enabled=True,
|
|
audio_in_enabled=True,
|
|
camera_out_enabled=False,
|
|
vad_enabled=True,
|
|
vad_audio_passthrough=True,
|
|
vad_analyzer=SileroVADAnalyzer(),
|
|
transcription_enabled=True,
|
|
#
|
|
# Spanish
|
|
#
|
|
# transcription_settings=DailyTranscriptionSettings(
|
|
# language="es",
|
|
# tier="nova",
|
|
# model="2-general"
|
|
# )
|
|
),
|
|
)
|
|
|
|
tts = ElevenLabsTTSService(
|
|
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
|
#
|
|
# English
|
|
#
|
|
voice_id="cgSgspJ2msm6clMCkdW9",
|
|
aiohttp_session=session,
|
|
#
|
|
# Spanish
|
|
#
|
|
# model="eleven_multilingual_v2",
|
|
# voice_id="gD1IexrzCvsXPHUuT0s3",
|
|
)
|
|
|
|
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
|
|
|
|
messages = [
|
|
{
|
|
"role": "system",
|
|
#
|
|
# English
|
|
#
|
|
"content": "You are Chatbot, a friendly, helpful robot. 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, but keep your responses brief. Start by introducing yourself. Keep all your response to 12 words or fewer.",
|
|
#
|
|
# Spanish
|
|
#
|
|
# "content": "Eres Chatbot, un amigable y útil robot. Tu objetivo es demostrar tus capacidades de una manera breve. Tus respuestas se convertiran a audio así que nunca no debes incluir caracteres especiales. Contesta a lo que el usuario pregunte de una manera creativa, útil y breve. Empieza por presentarte a ti mismo.",
|
|
},
|
|
]
|
|
|
|
context = OpenAILLMContext(messages)
|
|
context_aggregator = llm.create_context_aggregator(context)
|
|
|
|
audiobuffer = AudioBufferProcessor()
|
|
pipeline = Pipeline(
|
|
[
|
|
transport.input(), # microphone
|
|
context_aggregator.user(),
|
|
llm,
|
|
tts,
|
|
transport.output(),
|
|
audiobuffer, # used to buffer the audio in the pipeline
|
|
context_aggregator.assistant(),
|
|
]
|
|
)
|
|
|
|
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
|
|
|
|
@transport.event_handler("on_first_participant_joined")
|
|
async def on_first_participant_joined(transport, participant):
|
|
transport.capture_participant_transcription(participant["id"])
|
|
await task.queue_frames([LLMMessagesFrame(messages)])
|
|
|
|
@transport.event_handler("on_participant_left")
|
|
async def on_participant_left(transport, participant, reason):
|
|
print(f"Participant left: {participant}")
|
|
await task.queue_frame(EndFrame())
|
|
await save_audio(audiobuffer)
|
|
|
|
runner = PipelineRunner()
|
|
|
|
await runner.run(task)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(main())
|