From aa7a01451879527119f4709e1820f18fbf5a7b18 Mon Sep 17 00:00:00 2001 From: Mark Backman Date: Tue, 7 Apr 2026 09:35:13 -0400 Subject: [PATCH] Add mistral voice example --- examples/voice/voice-mistral.py | 127 ++++++++++++++++++++++++++++ src/pipecat/services/mistral/tts.py | 24 +----- 2 files changed, 129 insertions(+), 22 deletions(-) create mode 100644 examples/voice/voice-mistral.py diff --git a/examples/voice/voice-mistral.py b/examples/voice/voice-mistral.py new file mode 100644 index 000000000..9c8c8789b --- /dev/null +++ b/examples/voice/voice-mistral.py @@ -0,0 +1,127 @@ +# +# 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 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.mistral.tts import MistralTTSService +from pipecat.services.openai.llm import OpenAILLMService +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") + + stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY")) + + tts = MistralTTSService( + api_key=os.getenv("MISTRAL_API_KEY"), + settings=MistralTTSService.Settings( + voice="c69964a6-ab8b-4f8a-9465-ec0925096ec8", + ), + ) + + llm = OpenAILLMService( + api_key=os.getenv("OPENAI_API_KEY"), + settings=OpenAILLMService.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() diff --git a/src/pipecat/services/mistral/tts.py b/src/pipecat/services/mistral/tts.py index f2a49517a..7a9c7dea2 100644 --- a/src/pipecat/services/mistral/tts.py +++ b/src/pipecat/services/mistral/tts.py @@ -64,8 +64,6 @@ class MistralTTSService(TTSService): self, *, api_key: Optional[str] = None, - voice_id: Optional[str] = None, - model: Optional[str] = None, sample_rate: Optional[int] = None, settings: Optional[Settings] = None, **kwargs, @@ -75,38 +73,20 @@ class MistralTTSService(TTSService): Args: api_key: Mistral API key for authentication. If None, uses MISTRAL_API_KEY environment variable. - voice_id: Voice ID to use for synthesis. - - .. deprecated:: 0.0.105 - Use ``settings=MistralTTSService.Settings(voice=...)`` instead. - - model: TTS model to use. Defaults to "voxtral-mini-tts-2603". - - .. deprecated:: 0.0.105 - Use ``settings=MistralTTSService.Settings(model=...)`` instead. - sample_rate: Output audio sample rate in Hz. Audio is resampled from Mistral's native 24kHz when a different rate is requested. settings: Runtime-updatable settings. When provided alongside deprecated parameters, ``settings`` values take precedence. **kwargs: Additional keyword arguments passed to TTSService. """ - # 1. Initialize default_settings with hardcoded defaults + # Initialize default_settings with hardcoded defaults default_settings = self.Settings( model="voxtral-mini-tts-2603", voice=None, language=None, ) - # 2. Apply direct init arg overrides (deprecated) - if voice_id is not None: - self._warn_init_param_moved_to_settings("voice_id", "voice") - default_settings.voice = voice_id - if model is not None: - self._warn_init_param_moved_to_settings("model", "model") - default_settings.model = model - - # 3. Apply settings delta (canonical API, always wins) + # Apply settings delta (canonical API, always wins) if settings is not None: default_settings.apply_update(settings)