Resemble AI Text-to-Speech

Overview

ResembleAITTSService provides high-quality text-to-speech synthesis using Resemble AI’s streaming WebSocket API with word-level timestamps and audio context management for handling multiple simultaneous synthesis requests with proper interruption support.

Resemble AI TTS API Reference

Pipecat’s API methods for Resemble AI TTS integration

Example Implementation

Complete example with interruption handling

Resemble AI Documentation

Official Resemble AI API documentation

Sign up

Installation

To use Resemble AI services, install the required dependencies:

uv add "pipecat-ai[resembleai]"

Prerequisites

Resemble AI Account Setup

Before using Resemble AI TTS services, you need:

Resemble AI Account: Sign up at Resemble AI
API Key: Generate an API key from your account settings
Voice Selection: Choose or create voice UUIDs from your voice library

Required Environment Variables

RESEMBLE_API_KEY: Your Resemble AI API key for authentication

Configuration

ResembleAITTSService

str

required

Resemble AI API key for authentication.

str

default:"None"

deprecated

Deprecated since 0.0.105, removed in 2.0.0. Use settings=ResembleAITTSService.Settings(voice=...) instead.

ResembleAITTSService.Settings

default:"None"

Runtime-configurable settings. See Settings below.

str

default:"wss://websocket.cluster.resemble.ai/stream"

WebSocket URL for Resemble AI TTS API.

str

default:"PCM_16"

PCM bit depth. Options: PCM_32, PCM_24, PCM_16, or MULAW. The service pushes the audio as 16-bit PCM, so only PCM_16 plays correctly.

str

default:"wav"

Audio output format (wav or mp3). The service pushes the audio as raw PCM, so only wav plays correctly.

int

default:"22050"

Audio sample rate in Hz. Options: 8000, 16000, 22050, 32000, or 44100.

Settings

Runtime-configurable settings passed via the settings constructor argument using ResembleAITTSService.Settings(...). These can be updated mid-conversation with TTSUpdateSettingsFrame. See Service Settings for details.

Parameter	Type	Default	Description
`model`	`str`	`None`	Not sent by this service; reported only as the model name in metrics and traces. (Inherited.)
`voice`	`str`	`None`	Voice UUID. There is no default voice, so set one. (Inherited.)
`language`	`Language \| str`	`None`	Language used to split text into sentences; not sent to Resemble AI. (Inherited.)

Usage

Basic Setup

import os

from pipecat.services.resembleai.tts import ResembleAITTSService

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

With Custom Settings

from pipecat.services.resembleai.tts import ResembleAITTSService

tts = ResembleAITTSService(
    api_key=os.getenv("RESEMBLE_API_KEY"),
    settings=ResembleAITTSService.Settings(
        voice="your-voice-uuid",
    ),
    sample_rate=16000,
    precision="PCM_16",
    output_format="wav",
)

Notes

Word-level timestamps: Resemble AI provides word-level timing information, enabling synchronized text highlighting and precise interruption handling.
Jitter buffering: The service holds back the first 44,100 bytes of each response’s audio before pushing any, which delays the start of speech by about 1 second at the default 22050 Hz (about half a second at 44100 Hz).
Audio context management: Supports multiple simultaneous synthesis requests with proper context tracking and interruption handling.
Default sample rate: Defaults to 22050 Hz. Supported rates are 8000, 16000, 22050, 32000, and 44100 Hz.

Event Handlers

Resemble AI TTS supports the standard service connection events:

Event	Description
`on_connected`	Connected to Resemble AI WebSocket
`on_disconnected`	Disconnected from Resemble AI WebSocket
`on_connection_error`	WebSocket connection error occurred

@tts.event_handler("on_connected")
async def on_connected(service):
    print("Connected to Resemble AI")

Get Started

Pipecat Server

Client SDKs

Pipecat Flows

Pipecat Cloud

CLI

Pipecat Context Hub

Resemble AI Text-to-Speech

Overview

Resemble AI TTS API Reference

Example Implementation

Resemble AI Documentation

Sign up

Installation

Prerequisites

Resemble AI Account Setup

Required Environment Variables

Configuration

ResembleAITTSService

Settings

Usage

Basic Setup

With Custom Settings

Notes

Event Handlers

​Overview

Resemble AI TTS API Reference

Example Implementation

Resemble AI Documentation

Sign up

​Installation

​Prerequisites

​Resemble AI Account Setup

​Required Environment Variables

​Configuration

​ResembleAITTSService

​Settings

​Usage

​Basic Setup

​With Custom Settings

​Notes

​Event Handlers

Overview

Installation

Prerequisites

Resemble AI Account Setup

Required Environment Variables

Configuration

ResembleAITTSService

Settings

Usage

Basic Setup

With Custom Settings

Notes

Event Handlers