New `XAISTTService` wraps xAI's real-time speech-to-text WebSocket (`wss://api.x.ai/v1/stt`). It extends `WebsocketSTTService`, authenticates with the `XAI_API_KEY` as a Bearer token on the WS handshake, and streams raw audio (PCM/mu-law/A-law) with configurable interim results, endpointing, language, multichannel, and diarization settings. - `src/pipecat/services/xai/stt.py`: new service, settings dataclass, and `language_to_xai_stt_language` helper. - `src/pipecat/services/stt_latency.py`: `XAI_TTFS_P99` default. - `pyproject.toml` / `uv.lock`: `xai` extra now pulls in `websockets-base`. - `README.md`: link to xAI STT in the services table. - `examples/voice/voice-xai.py`: swap DeepgramSTTService for XAISTTService so the xAI voice example is fully xAI. - `examples/transcription/transcription-xai.py`: new transcription-only example using the new service.
90 lines
2.6 KiB
Python
90 lines
2.6 KiB
Python
#
|
|
# Copyright (c) 2024-2026, Daily
|
|
#
|
|
# SPDX-License-Identifier: BSD 2-Clause License
|
|
#
|
|
|
|
import os
|
|
|
|
from dotenv import load_dotenv
|
|
from loguru import logger
|
|
|
|
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
|
from pipecat.frames.frames import Frame, TranscriptionFrame
|
|
from pipecat.pipeline.pipeline import Pipeline
|
|
from pipecat.pipeline.runner import PipelineRunner
|
|
from pipecat.pipeline.task import PipelineTask
|
|
from pipecat.processors.audio.vad_processor import VADProcessor
|
|
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
|
from pipecat.runner.types import RunnerArguments
|
|
from pipecat.runner.utils import create_transport
|
|
from pipecat.services.xai.stt import XAISTTService
|
|
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)
|
|
|
|
|
|
class TranscriptionLogger(FrameProcessor):
|
|
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
|
await super().process_frame(frame, direction)
|
|
|
|
if isinstance(frame, TranscriptionFrame):
|
|
print(f"Transcription: {frame.text}")
|
|
|
|
# Push all frames through
|
|
await self.push_frame(frame, direction)
|
|
|
|
|
|
transport_params = {
|
|
"daily": lambda: DailyParams(
|
|
audio_in_enabled=True,
|
|
),
|
|
"twilio": lambda: FastAPIWebsocketParams(
|
|
audio_in_enabled=True,
|
|
),
|
|
"webrtc": lambda: TransportParams(
|
|
audio_in_enabled=True,
|
|
),
|
|
}
|
|
|
|
|
|
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
|
logger.info(f"Starting bot")
|
|
|
|
stt = XAISTTService(
|
|
api_key=os.getenv("XAI_API_KEY"),
|
|
)
|
|
|
|
tl = TranscriptionLogger()
|
|
vad_processor = VADProcessor(vad_analyzer=SileroVADAnalyzer())
|
|
|
|
pipeline = Pipeline([transport.input(), vad_processor, stt, tl])
|
|
|
|
task = PipelineTask(
|
|
pipeline,
|
|
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
|
)
|
|
|
|
@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()
|