Align Together STT/TTS services with Pipecat patterns
STT: - Add Settings class alias and 4-step init pattern - Add resampler to convert pipeline audio to 16kHz for Together API - Add keepalive support and _update_settings with reconnect - Pass language to transcription frames - Remove unnecessary OpenAI-Beta header TTS: - Add Settings class alias and 4-step init pattern - Use push_start_frame=True for base class audio context management - Route audio through append_to_audio_context instead of push_frame - Track pending commits for proper audio context lifecycle - Replace _handle_interruption with on_audio_context_interrupted - Add _update_settings with reconnect - Guard against stale audio after interruption
This commit is contained in:
@@ -21,7 +21,6 @@ from pipecat.processors.aggregators.llm_response_universal import (
|
||||
)
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.together.llm import TogetherLLMService
|
||||
from pipecat.services.together.stt import TogetherSTTService
|
||||
from pipecat.services.together.tts import TogetherTTSService
|
||||
@@ -55,12 +54,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
|
||||
stt = TogetherSTTService(api_key=os.getenv("TOGETHER_API_KEY"))
|
||||
|
||||
tts = TogetherTTSService(api_key=os.getenv("TOGETHER_API_KEY"))
|
||||
tts = TogetherTTSService(
|
||||
api_key=os.getenv("TOGETHER_API_KEY"),
|
||||
settings=TogetherTTSService.Settings(
|
||||
voice="tara",
|
||||
),
|
||||
)
|
||||
|
||||
llm = TogetherLLMService(
|
||||
api_key=os.getenv("TOGETHER_API_KEY"),
|
||||
settings=TogetherLLMService.Settings(
|
||||
model="Qwen/Qwen3.5-9B",
|
||||
model="openai/gpt-oss-120b",
|
||||
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
),
|
||||
)
|
||||
|
||||
83
examples/foundational/13n-together-transcription.py
Normal file
83
examples/foundational/13n-together-transcription.py
Normal file
@@ -0,0 +1,83 @@
|
||||
#
|
||||
# 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.together.stt import TogetherSTTService
|
||||
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 use lambdas to defer transport parameter creation until the transport
|
||||
# type is selected at runtime.
|
||||
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 = TogetherSTTService(api_key=os.getenv("TOGETHER_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()
|
||||
Reference in New Issue
Block a user