tts

Together AI text-to-speech service implementation.

This module provides a TTS service using Together AI’s WebSocket API:

  • TogetherTTSService: WebSocket-based real-time TTS with streaming audio output.

class pipecat.services.together.tts.TogetherTTSSettings(model: str | None | _NotGiven = <factory>, extra: dict[str, ~typing.Any]=<factory>, voice: str | None | _NotGiven = <factory>, language: Language | str | None | _NotGiven = <factory>, max_partial_length: int | None | _NotGiven = <factory>)[source]

Bases: TTSSettings

Settings for the Together AI TTS service.

Parameters:

max_partial_length – Maximum partial text length for streaming.

max_partial_length: int | None | _NotGiven
class pipecat.services.together.tts.TogetherTTSService(*, api_key: str, url: str = 'wss://api.together.ai/v1/audio/speech/websocket', sample_rate: int | None = 24000, settings: TogetherTTSSettings | None = None, **kwargs)[source]

Bases: WebsocketTTSService

Together AI TTS service with WebSocket streaming.

Provides text-to-speech using Together AI’s realtime WebSocket API. Supports streaming synthesis with configurable voice and model options.

Example:

tts = TogetherTTSService(
    api_key="your-api-key",
    settings=TogetherTTSService.Settings(
        voice="tara",
        model="canopylabs/orpheus-3b-0.1-ft",
    ),
)
Settings

alias of TogetherTTSSettings

__init__(*, api_key: str, url: str = 'wss://api.together.ai/v1/audio/speech/websocket', sample_rate: int | None = 24000, settings: TogetherTTSSettings | None = None, **kwargs)[source]

Initialize the Together AI TTS service.

Parameters:

  • api_key – Together AI API key for authentication.

  • url – WebSocket URL for Together AI TTS API.

  • sample_rate – Output sample rate for emitted PCM frames. Defaults to 24000; Together streams at 24 kHz and does not support other rates.

  • settings – Runtime-updatable settings for the TTS service.

  • **kwargs – Additional arguments passed to WebsocketTTSService.

can_generate_metrics() → bool[source]

Check if this service can generate processing metrics.

language_to_service_language(language: Language) → str | None[source]

Convert a Language enum to Together AI language format.

Parameters:

language – The language to convert.

Returns:

The language code string, or None if not supported.

async start(frame: StartFrame)[source]

Start the Together AI TTS service.

Parameters:

frame – The start frame containing initialization parameters.

async stop(frame: EndFrame)[source]

Stop the Together AI TTS service.

Parameters:

frame – The end frame.

async cancel(frame: CancelFrame)[source]

Cancel the Together AI TTS service.

Parameters:

frame – The cancel frame.

async flush_audio(context_id: str | None = None)[source]

Flush any pending audio by committing the text buffer.

async on_audio_context_interrupted(context_id: str)[source]

Clear the Together AI text buffer when the bot is interrupted.

Parameters:

context_id – The ID of the audio context that was interrupted.

async run_tts(text: str, context_id: str) → AsyncGenerator[Frame | None, None][source]

Generate speech from text using Together AI’s streaming API.

Parameters:

  • text – The text to synthesize into speech.

  • context_id – The context ID for tracking audio frames.

Yields:

Frame – Audio arrives via the WebSocket receive task.

async setup(setup: FrameProcessorSetup)

Set up the processor with required components.

Parameters:

setup – Configuration object containing setup parameters.