wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Code review fixes + docstrings

Browse Source
This commit is contained in:
Mark Backman
2025-01-17 20:11:16 -05:00
parent d51893f61c
commit b81323d676
2 changed files with 17 additions and 126 deletions
Download Patch File Download Diff File Expand all files Collapse all files

104
examples/foundational/07d-interruptible-elevenlabs-http.py
View File

@@ -1,104 +0,0 @@
#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import asyncio
import os
import sys
import aiohttp
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
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.services.elevenlabs import ElevenLabsHttpTTSService
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 main():
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,
"Respond bot",
DailyParams(
audio_out_enabled=True,
transcription_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
)
tts = ElevenLabsHttpTTSService(
api_key=os.getenv("ELEVENLABS_API_KEY", ""),
voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
# params=ElevenLabsHttpTTSService.InputParams(language="en"),
)
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
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
context_aggregator.user(), # User responses
llm, # LLM
tts, # TTS
transport.output(), # Transport bot output
context_aggregator.assistant(), # Assistant spoken responses
]
)
task = PipelineTask(
pipeline,
PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
await transport.capture_participant_transcription(participant["id"])
# 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()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()
await runner.run(task)
if __name__ == "__main__":
asyncio.run(main())

39
src/pipecat/services/elevenlabs.py
View File

@@ -430,6 +430,7 @@ class ElevenLabsHttpTTSService(TTSService):
Args:
api_key: ElevenLabs API key
voice_id: ID of the voice to use
aiohttp_session: aiohttp ClientSession
model: Model ID (default: "eleven_flash_v2_5" for low latency)
base_url: API base URL
output_format: Audio output format (PCM)
@@ -449,20 +450,20 @@ class ElevenLabsHttpTTSService(TTSService):
*,
api_key: str,
voice_id: str,
aiohttp_session: aiohttp.ClientSession,
model: str = "eleven_flash_v2_5",
base_url: str = "https://api.elevenlabs.io",
output_format: ElevenLabsOutputFormat = "pcm_24000",
params: InputParams = InputParams(),
**kwargs,
):
sample_rate = sample_rate_from_output_format(output_format)
super().__init__(sample_rate=sample_rate, **kwargs)
super().__init__(sample_rate=sample_rate_from_output_format(output_format), **kwargs)
self._api_key = api_key
self._base_url = base_url
self._output_format = output_format
self._params = params
self._session: Optional[aiohttp.ClientSession] = None
self._session = aiohttp_session
self._settings = {
"sample_rate": sample_rate_from_output_format(output_format),
@@ -484,6 +485,11 @@ class ElevenLabsHttpTTSService(TTSService):
return True
def _set_voice_settings(self) -> Optional[Dict[str, Union[float, bool]]]:
"""Configure voice settings if stability and similarity_boost are provided.
Returns:
Dictionary of voice settings or None if required parameters are missing.
"""
voice_settings: Dict[str, Union[float, bool]] = {}
if (
self._settings["stability"] is not None
@@ -507,27 +513,16 @@ class ElevenLabsHttpTTSService(TTSService):
return voice_settings or None
async def start(self, frame: StartFrame):
await super().start(frame)
self._session = aiohttp.ClientSession()
async def stop(self, frame: EndFrame):
await super().stop(frame)
if self._session:
await self._session.close()
self._session = None
async def cancel(self, frame: CancelFrame):
await super().cancel(frame)
if self._session:
await self._session.close()
self._session = None
async def run_tts(self, text: str) -> AsyncGenerator[Frame, None]:
logger.debug(f"Generating TTS: [{text}]")
"""Generate speech from text using ElevenLabs streaming API.
if not self._session:
self._session = aiohttp.ClientSession()
Args:
text: The text to convert to speech
Yields:
Frames containing audio data and status information
"""
logger.debug(f"Generating TTS: [{text}]")
url = f"{self._base_url}/v1/text-to-speech/{self._voice_id}/stream"