Skip to main content

​
Overview

Async provides high-quality text-to-speech synthesis with two service implementations: AsyncAITTSService (WebSocket-based) for real-time streaming with interruption support, and AsyncAIHttpTTSService (HTTP-based) for simpler synthesis. AsyncAITTSService is recommended for interactive applications requiring low latency.

AsyncAI TTS API Reference

Pipecat’s API methods for AsyncAI TTS integration

Example Implementation

Complete example with WebSocket streaming

Async Documentation

Official Async API documentation

Voice Models

Explore available voice models and features

​
Installation

To use Async services, install the required dependencies: 
pip install "pipecat-ai[asyncai]"

​
Prerequisites

​
Async Account Setup

Before using Async TTS services, you need:
  1. Async Account: Sign up at Async
  2. API Key: Generate an API key from your account dashboard
  3. Voice Selection: Choose from available voice models

​
Required Environment Variables

  • ASYNCAI_API_KEY: Your Async API key for authentication

​
Configuration

​
AsyncAITTSService

​
api_key
str
required
Async API key.
​
voice_id
str
required
deprecated
UUID of the voice to use for synthesis. Deprecated in v0.0.105. Use settings=AsyncAITTSService.Settings(voice=...) instead.
​
model
str
default:"async_flash_v1.0"
deprecated
TTS model to use. Deprecated in v0.0.105. Use settings=AsyncAITTSService.Settings(model=...) instead.
​
version
str
default:"v1"
Async API version.
​
url
str
default:"wss://api.async.com/text_to_speech/websocket/ws"
WebSocket endpoint URL.
​
sample_rate
int
default:"None"
Output audio sample rate in Hz. When None, uses the pipeline’s configured sample rate.
​
encoding
str
default:"pcm_s16le"
Audio encoding format.
​
container
str
default:"raw"
Audio container format.
​
text_aggregation_mode
TextAggregationMode
default:"TextAggregationMode.SENTENCE"
Controls how incoming text is aggregated before synthesis. SENTENCE (default) buffers text until sentence boundaries, producing more natural speech. TOKEN streams tokens directly for lower latency. Import from pipecat.services.tts_service.
​
aggregate_sentences
bool
default:"None"
deprecated
Deprecated in v0.0.104. Use text_aggregation_mode instead.
​
params
InputParams
default:"None"
deprecated
Deprecated in v0.0.105. Use settings=AsyncAITTSService.Settings(...) instead.
​
settings
AsyncAITTSService.Settings
default:"None"
Runtime-configurable settings. See Settings below.

​
AsyncAIHttpTTSService

The HTTP service accepts similar parameters to the WebSocket service, with these differences:
​
aiohttp_session
aiohttp.ClientSession
required
An aiohttp session for HTTP requests. You must create and manage this yourself.
​
url
str
default:"https://api.async.com"
HTTP API base URL (instead of WebSocket URL).

​
Settings

Runtime-configurable settings passed via the settings constructor argument using AsyncAITTSService.Settings(...). These can be updated mid-conversation with TTSUpdateSettingsFrame. See Service Settings for details.
ParameterTypeDefaultDescription
modelstrNoneModel identifier. (Inherited.)
voicestrNoneVoice identifier. (Inherited.)
languageLanguage | strNoneLanguage for synthesis. (Inherited.)

​
Usage

​
Basic Setup

from pipecat.services.asyncai import AsyncAITTSService

tts = AsyncAITTSService(
    api_key=os.getenv("ASYNCAI_API_KEY"),
    settings=AsyncAITTSService.Settings(
        voice="your-voice-uuid",
    ),
)

​
With Language Customization

from pipecat.transcriptions.language import Language

tts = AsyncAITTSService(
    api_key=os.getenv("ASYNCAI_API_KEY"),
    settings=AsyncAITTSService.Settings(
        voice="your-voice-uuid",
        model="async_flash_v1.0",
        language=Language.ES,
    ),
)

​
HTTP Service

import aiohttp
from pipecat.services.asyncai import AsyncAIHttpTTSService

async with aiohttp.ClientSession() as session:
    tts = AsyncAIHttpTTSService(
        api_key=os.getenv("ASYNCAI_API_KEY"),
        settings=AsyncAIHttpTTSService.Settings(
            voice="your-voice-uuid",
        ),
        aiohttp_session=session,
    )
The InputParams / params= pattern is deprecated as of v0.0.105. Use Settings / settings= instead. See the Service Settings guide for migration details.

​
Event Handlers

Async TTS supports the standard service connection events:
EventDescription
on_connectedConnected to Async WebSocket
on_disconnectedDisconnected from Async WebSocket
on_connection_errorWebSocket connection error occurred
@tts.event_handler("on_connected")
async def on_connected(service):
    print("Connected to Async")