d8f5c0be71
Adds XAITTSService in the existing xai/tts.py module, alongside the existing XAIHttpTTSService. Connects to xAI's streaming endpoint at wss://api.x.ai/v1/tts, streams text.delta chunks up and base64 audio.delta chunks down on the same connection so audio starts flowing before the full utterance is synthesized. Extends InterruptibleTTSService since xAI's protocol is strictly sequential per connection and exposes neither a cancel verb nor a context ID — the only way to stop an in-flight utterance is to tear down the WebSocket, which is exactly what InterruptibleTTSService does on interruption when the bot is speaking. Voice, language, codec, and sample_rate are passed as query-string params at connect time; runtime setting changes reconnect the socket. Defaults to raw PCM so emitted TTSAudioRawFrame objects need no decoding downstream. Splits the existing example into voice-xai.py (WebSocket) and voice-xai-http.py (batch HTTP) so each variant has its own entry point. Promotes the xai extra to depend on pipecat-ai[websockets-base] since the new service imports the websockets library.
129 lines
4.2 KiB
Python
129 lines
4.2 KiB
Python
#
|
|
# Copyright (c) 2024-2026, Daily
|
|
#
|
|
# SPDX-License-Identifier: BSD 2-Clause License
|
|
#
|
|
|
|
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 LLMRunFrame
|
|
from pipecat.pipeline.pipeline import Pipeline
|
|
from pipecat.pipeline.runner import PipelineRunner
|
|
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
|
from pipecat.processors.aggregators.llm_context import LLMContext
|
|
from pipecat.processors.aggregators.llm_response_universal import (
|
|
LLMContextAggregatorPair,
|
|
LLMUserAggregatorParams,
|
|
)
|
|
from pipecat.runner.types import RunnerArguments
|
|
from pipecat.runner.utils import create_transport
|
|
from pipecat.services.deepgram.stt import DeepgramSTTService
|
|
from pipecat.services.xai.llm import GrokLLMService
|
|
from pipecat.services.xai.tts import XAIHttpTTSService
|
|
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
|
from pipecat.transports.daily.transport import DailyParams
|
|
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
|
|
|
load_dotenv(override=True)
|
|
|
|
# We use lambdas to defer transport parameter creation until the transport
|
|
# type is selected at runtime.
|
|
transport_params = {
|
|
"daily": lambda: DailyParams(
|
|
audio_in_enabled=True,
|
|
audio_out_enabled=True,
|
|
),
|
|
"twilio": lambda: FastAPIWebsocketParams(
|
|
audio_in_enabled=True,
|
|
audio_out_enabled=True,
|
|
),
|
|
"webrtc": lambda: TransportParams(
|
|
audio_in_enabled=True,
|
|
audio_out_enabled=True,
|
|
),
|
|
}
|
|
|
|
|
|
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
|
logger.info(f"Starting bot")
|
|
|
|
async with aiohttp.ClientSession() as session:
|
|
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
|
|
|
tts = XAIHttpTTSService(
|
|
api_key=os.getenv("XAI_API_KEY"),
|
|
aiohttp_session=session,
|
|
settings=XAIHttpTTSService.Settings(
|
|
voice="eve",
|
|
),
|
|
)
|
|
|
|
llm = GrokLLMService(
|
|
api_key=os.getenv("XAI_API_KEY"),
|
|
settings=GrokLLMService.Settings(
|
|
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
|
),
|
|
)
|
|
|
|
context = LLMContext()
|
|
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
|
context,
|
|
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
|
)
|
|
|
|
pipeline = Pipeline(
|
|
[
|
|
transport.input(), # Transport user input
|
|
stt,
|
|
user_aggregator, # User responses
|
|
llm, # LLM
|
|
tts, # TTS
|
|
transport.output(), # Transport bot output
|
|
assistant_aggregator, # Assistant spoken responses
|
|
]
|
|
)
|
|
|
|
task = PipelineTask(
|
|
pipeline,
|
|
params=PipelineParams(
|
|
enable_metrics=True,
|
|
enable_usage_metrics=True,
|
|
),
|
|
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
|
)
|
|
|
|
@transport.event_handler("on_client_connected")
|
|
async def on_client_connected(transport, client):
|
|
logger.info(f"Client connected")
|
|
# Kick off the conversation.
|
|
context.add_message(
|
|
{"role": "developer", "content": "Please introduce yourself to the user."}
|
|
)
|
|
await task.queue_frames([LLMRunFrame()])
|
|
|
|
@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()
|