tts

XTTS text-to-speech service implementation.

This module provides integration with Coqui XTTS streaming server for text-to-speech synthesis using local Docker deployment.

pipecat.services.xtts.tts.language_to_xtts_language(language: Language) → str | None[source]

Convert a Language enum to XTTS language code.

Parameters:

language – The Language enum value to convert.

Returns:

The corresponding XTTS language code, or None if not supported.

class pipecat.services.xtts.tts.XTTSTTSSettings(model: str | None | _NotGiven = <factory>, extra: dict[str, Any]=<factory>, voice: str | None | _NotGiven = <factory>, language: Language | str | None | _NotGiven = <factory>)[source]

Bases: TTSSettings

Settings for XTTSService.

class pipecat.services.xtts.tts.XTTSService(*, voice_id: str | None = None, base_url: str, aiohttp_session: ClientSession, language: Language = Language.EN, sample_rate: int | None = None, settings: XTTSTTSSettings | None = None, **kwargs)[source]

Bases: TTSService

Coqui XTTS text-to-speech service.

Provides text-to-speech synthesis using a locally running Coqui XTTS streaming server. Supports multiple languages and voice cloning through studio speakers configuration.

Settings

alias of XTTSTTSSettings

__init__(*, voice_id: str | None = None, base_url: str, aiohttp_session: ClientSession, language: Language = Language.EN, sample_rate: int | None = None, settings: XTTSTTSSettings | None = None, **kwargs)[source]

Initialize the XTTS service.

Parameters:

  • voice_id –

    ID of the voice/speaker to use for synthesis.

    Deprecated since version 0.0.105: Use settings=XTTSService.Settings(voice=...) instead.

  • base_url – Base URL of the XTTS streaming server.

  • aiohttp_session – HTTP session for making requests to the server.

  • language –

    Language for synthesis. Defaults to English.

    Deprecated since version 0.0.106: Use settings=XTTSService.Settings(language=...) instead.

  • sample_rate – Audio sample rate. If None, uses default.

  • settings – Runtime-updatable settings. When provided alongside deprecated parameters, settings values take precedence.

  • **kwargs – Additional arguments passed to parent TTSService.

can_generate_metrics() → bool[source]

Check if this service can generate processing metrics.

Returns:

True, as XTTS service supports metrics generation.

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

Convert a Language enum to XTTS service language format.

Parameters:

language – The language to convert.

Returns:

The XTTS-specific language code, or None if not supported.

async start(frame: StartFrame)[source]

Start the XTTS service and load studio speakers.

Parameters:

frame – The start frame containing initialization parameters.

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

Generate speech from text using XTTS streaming server.

Parameters:

  • text – The text to synthesize into speech.

  • context_id – The context ID for tracking audio frames.

Yields:

Frame – Audio frames containing the synthesized speech.