Add ElevenLabsSTTService

This commit is contained in:
Mark Backman
2025-09-23 09:32:28 -04:00
parent a19b9f70c0
commit cbce2075eb
6 changed files with 479 additions and 5 deletions

View File

@@ -24,6 +24,7 @@ from pipecat.processors.aggregators.llm_response_universal import LLMContextAggr
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.elevenlabs.stt import ElevenLabsSTTService
from pipecat.services.elevenlabs.tts import ElevenLabsHttpTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -63,7 +64,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# Create an HTTP session
async with aiohttp.ClientSession() as session:
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = ElevenLabsSTTService(
api_key=os.getenv("ELEVENLABS_API_KEY"),
aiohttp_session=session,
)
tts = ElevenLabsHttpTTSService(
api_key=os.getenv("ELEVENLABS_API_KEY", ""),

View File

@@ -0,0 +1,89 @@
#
# Copyright (c) 20242025, 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 Frame, TranscriptionFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.elevenlabs.stt import ElevenLabsSTTService
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)
# 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, vad_analyzer=SileroVADAnalyzer()),
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True, vad_analyzer=SileroVADAnalyzer()
),
"webrtc": lambda: TransportParams(audio_in_enabled=True, vad_analyzer=SileroVADAnalyzer()),
}
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
async with aiohttp.ClientSession() as session:
stt = ElevenLabsSTTService(
api_key=os.getenv("ELEVENLABS_API_KEY"),
aiohttp_session=session,
)
tl = TranscriptionLogger()
pipeline = Pipeline([transport.input(), 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()