tts

Async text-to-speech service implementations.

pipecat.services.asyncai.tts.language_to_async_language(language: Language) → str | None[source]

Convert a Language enum to Async language code.

Parameters:: language – The Language enum value to convert.
Returns:: The corresponding Async language code, or None if not supported.

Bases: TTSSettings

Settings for AsyncAITTSService and AsyncAIHttpTTSService.

class pipecat.services.asyncai.tts.AsyncAITTSService(*, api_key: str, voice_id: str | None = None, version: str = 'v1', url: str = 'wss://api.async.com/text_to_speech/websocket/ws', model: str | None = None, sample_rate: int | None = None, encoding: str = 'pcm_s16le', container: str = 'raw', params: InputParams | None = None, settings: AsyncAITTSSettings | None = None, aggregate_sentences: bool | None = None, text_aggregation_mode: TextAggregationMode | None = None, **kwargs)[source]

Bases: WebsocketTTSService

Async TTS service with WebSocket streaming.

Provides text-to-speech using Async’s streaming WebSocket API.

Settings: alias of AsyncAITTSSettings

class InputParams(*, language: Language | None = None)[source]

Bases: BaseModel

Input parameters for Async TTS configuration.

Deprecated since version 0.0.105: Use AsyncAITTSService.Settings directly via the settings parameter instead.

Parameters:: language – Language to use for synthesis.

language: Language | None

__init__(*, api_key: str, voice_id: str | None = None, version: str = 'v1', url: str = 'wss://api.async.com/text_to_speech/websocket/ws', model: str | None = None, sample_rate: int | None = None, encoding: str = 'pcm_s16le', container: str = 'raw', params: InputParams | None = None, settings: AsyncAITTSSettings | None = None, aggregate_sentences: bool | None = None, text_aggregation_mode: TextAggregationMode | None = None, **kwargs)[source]

Initialize the Async TTS service.

Parameters:

api_key – Async API key.
voice_id –
UUID of the voice to use for synthesis. See docs for a full list: https://docs.async.com/list-voices-16699698e0

Deprecated since version 0.0.105: Use settings=AsyncAITTSService.Settings(voice=...) instead.
version – Async API version.
url – WebSocket URL for Async TTS API.
model –
TTS model to use (e.g., “async_flash_v1.0”).

Deprecated since version 0.0.105: Use settings=AsyncAITTSService.Settings(model=...) instead.
sample_rate – Audio sample rate.
encoding – Audio encoding format.
container – Audio container format.
params –
Additional input parameters for voice customization.

Deprecated since version 0.0.105: Use settings=AsyncAITTSService.Settings(...) instead.
settings – Runtime-updatable settings. When provided alongside deprecated parameters, settings values take precedence.
aggregate_sentences –
Deprecated. Use text_aggregation_mode instead.

Deprecated since version 0.0.104: Use text_aggregation_mode instead.
text_aggregation_mode – How to aggregate text before synthesis.
**kwargs – Additional arguments passed to the parent service.

can_generate_metrics() → bool[source]

Check if this service can generate processing metrics.

Returns:: True, as Async service supports metrics generation.

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

Convert a Language enum to Async language format.

Parameters:: language – The language to convert.
Returns:: The Async-specific language code, or None if not supported.

async start(frame: StartFrame)[source]

Start the Async TTS service.

Parameters:: frame – The start frame containing initialization parameters.

async stop(frame: EndFrame)[source]

Stop the Async TTS service.

Parameters:: frame – The end frame.

async cancel(frame: CancelFrame)[source]

Cancel the Async TTS service.

Parameters:: frame – The cancel frame.

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

Flush any pending audio.

Parameters:: context_id – The specific context to flush. If None, falls back to the currently active context.

async push_frame(frame: Frame, direction: FrameDirection = FrameDirection.DOWNSTREAM)[source]

Push a frame downstream with special handling for stop conditions.

Parameters:

frame – The frame to push.
direction – The direction to push the frame.

async on_audio_context_interrupted(context_id: str)[source]: Close the Async AI context when the bot is interrupted.

async on_audio_context_completed(context_id: str)[source]

Close the Async AI context after all audio has been played.

Async AI does not send a server-side signal when a context is exhausted, so Pipecat must explicitly close it with close_context: True to free server-side resources.

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

Generate speech from text using Async API websocket endpoint.

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.

class pipecat.services.asyncai.tts.AsyncAIHttpTTSService(*, api_key: str, voice_id: str | None = None, aiohttp_session: ClientSession, model: str | None = None, url: str = 'https://api.async.com', version: str = 'v1', sample_rate: int | None = None, encoding: str = 'pcm_s16le', container: str = 'raw', params: InputParams | None = None, settings: AsyncAITTSSettings | None = None, **kwargs)[source]

Bases: TTSService

HTTP-based Async TTS service.

Provides text-to-speech using Async’s HTTP streaming API for simpler, non-WebSocket integration. Suitable for use cases where streaming WebSocket connection is not required or desired.

Settings: alias of AsyncAITTSSettings

class InputParams(*, language: Language | None = None)[source]

Bases: BaseModel

Input parameters for Async API.

Deprecated since version 0.0.105: Use AsyncAIHttpTTSService.Settings directly via the settings parameter instead.

Parameters:: language – Language to use for synthesis.

language: Language | None

__init__(*, api_key: str, voice_id: str | None = None, aiohttp_session: ClientSession, model: str | None = None, url: str = 'https://api.async.com', version: str = 'v1', sample_rate: int | None = None, encoding: str = 'pcm_s16le', container: str = 'raw', params: InputParams | None = None, settings: AsyncAITTSSettings | None = None, **kwargs)[source]

Initialize the Async TTS service.

Parameters:

api_key – Async API key.
voice_id –
ID of the voice to use for synthesis.

Deprecated since version 0.0.105: Use settings=AsyncAIHttpTTSService.Settings(voice=...) instead.
aiohttp_session – An aiohttp session for making HTTP requests.
model –
TTS model to use (e.g., “async_flash_v1.0”).

Deprecated since version 0.0.105: Use settings=AsyncAIHttpTTSService.Settings(model=...) instead.
url – Base URL for Async API.
version – API version string for Async API.
sample_rate – Audio sample rate.
encoding – Audio encoding format.
container – Audio container format.
params –
Additional input parameters for voice customization.

Deprecated since version 0.0.105: Use settings=AsyncAIHttpTTSService.Settings(...) instead.
settings – Runtime-updatable settings. When provided alongside deprecated parameters, settings values take precedence.
**kwargs – Additional arguments passed to the parent TTSService.

can_generate_metrics() → bool[source]

Check if this service can generate processing metrics.

Returns:: True, as Async HTTP service supports metrics generation.

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

Convert a Language enum to Async language format.

Parameters:: language – The language to convert.
Returns:: The Async-specific language code, or None if not supported.

async start(frame: StartFrame)[source]

Start the Async HTTP TTS service.

Parameters:: frame – The start frame containing initialization parameters.

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

Generate speech from text using Async’s HTTP streaming API.

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.