6d582e41b7
* Added Sarvam TTS Websocket Implementation * Addressed some of the comments on PR * added change voice logic * added changes from main * pushing text frames and added flush audio * updated docs string for better docs * Addressed comments and added some improvements * pushed optional args down * removed new line * made aiohttp session mandatory in http service * added push frame and removed unused function * removed pong message * added disconnecting logic --------- Co-authored-by: vinayak-sarvam <vinayak@sarvam.ai>
128 lines
4.1 KiB
Python
128 lines
4.1 KiB
Python
#
|
||
# Copyright (c) 2024–2025, Daily
|
||
#
|
||
# SPDX-License-Identifier: BSD 2-Clause License
|
||
#
|
||
|
||
|
||
import asyncio
|
||
import os
|
||
|
||
import aiohttp
|
||
from dotenv import load_dotenv
|
||
from loguru import logger
|
||
|
||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||
from pipecat.frames.frames import TTSUpdateSettingsFrame
|
||
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.runner.types import RunnerArguments
|
||
from pipecat.runner.utils import create_transport
|
||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||
from pipecat.services.openai.llm import OpenAILLMService
|
||
from pipecat.services.sarvam.tts import SarvamTTSService
|
||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||
from pipecat.transports.services.daily import DailyParams
|
||
|
||
load_dotenv(override=True)
|
||
|
||
|
||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||
# instantiated. The function will be called when the desired transport gets
|
||
# selected.
|
||
transport_params = {
|
||
"daily": lambda: DailyParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
vad_analyzer=SileroVADAnalyzer(),
|
||
),
|
||
"twilio": lambda: FastAPIWebsocketParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
vad_analyzer=SileroVADAnalyzer(),
|
||
),
|
||
"webrtc": lambda: TransportParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
vad_analyzer=SileroVADAnalyzer(),
|
||
),
|
||
}
|
||
|
||
|
||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||
logger.info(f"Starting bot")
|
||
|
||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||
|
||
tts = SarvamTTSService(
|
||
api_key=os.getenv("SARVAM_API_KEY"),
|
||
model="bulbul:v2",
|
||
voice_id="manisha",
|
||
)
|
||
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,
|
||
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(
|
||
enable_metrics=True,
|
||
enable_usage_metrics=True,
|
||
),
|
||
)
|
||
|
||
@transport.event_handler("on_client_connected")
|
||
async def on_client_connected(transport, client):
|
||
logger.info(f"Client connected")
|
||
# 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()])
|
||
|
||
# Optionally, you can wait for 30 seconds and then change the voice.
|
||
# await asyncio.sleep(30)
|
||
# await task.queue_frame(TTSUpdateSettingsFrame(settings={"voice": "anushka"}))
|
||
|
||
@transport.event_handler("on_client_disconnected")
|
||
async def on_client_disconnected(transport, client):
|
||
logger.info(f"Client disconnected")
|
||
await task.cancel()
|
||
|
||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||
|
||
await runner.run(task)
|
||
|
||
|
||
async def bot(runner_args: RunnerArguments):
|
||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||
transport = await create_transport(runner_args, transport_params)
|
||
await run_bot(transport, runner_args)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
from pipecat.runner.run import main
|
||
|
||
main()
|