devnen/Chatterbox-TTS-Server

Self-host the powerful Chatterbox TTS model. This server offers a user-friendly Web UI, flexible API endpoints (incl. OpenAI compatible), predefined voices, voice cloning, and large audiobook-scale text processing. Runs accelerated on NVIDIA (CUDA), AMD (ROCm), and CPU.

What it solves

Chatterbox TTS Server provides a user-friendly way to self-host Resemble AI's Chatterbox text-to-speech family. It simplifies the deployment and use of these models, adding a modern Web UI and an OpenAI-compatible API to make high-quality voice generation accessible without complex manual setup.

How it works

The project wraps the chatterbox-tts engine in a FastAPI server. It supports three distinct models: the high-quality Original Chatterbox (English), Chatterbox Multilingual (23 languages), and Chatterbox-Turbo (a streamlined, fast model). Users can switch between these engines via a hot-swappable selector in the UI. The server handles hardware acceleration across NVIDIA, AMD, and Apple Silicon GPUs, and includes an intelligent chunking system that splits long texts into manageable pieces to generate seamless audiobooks or long-form narration.

Who it’s for

Developers building voice agents, creators producing audiobooks, and users wanting to an expressive, self-hosted TTS system with voice cloning and multilingual support.

Highlights

  • Multi-Engine Support: Hot-swap between Original, Multilingual, and Turbo models without restarting the server.
  • Expressive Voice Control: Chatterbox-Turbo supports paralinguistic tags like [laugh], [cough], and [chuckle] for natural reactions.
  • Audiobook Generation: Intelligent text chunking allows for the processing of entire books into a single audio file.
  • Broad Hardware Compatibility: Native support for CUDA, ROCm, and Apple MPS, including a portable Windows mode that requires no system Python installation.
  • OpenAI-Compatible API: Allows easy integration into existing AI workflows and applications.

Related

  • Project
    resemble-ai/chatterbox

    A family of open-source text-to-speech models providing low-latency voice cloning and multilingual speech generation across various model sizes for GPU and CPU deployment.

  • Project
    rsxdalv/TTS-WebUI

    A unified web interface and manager for a wide variety of open-source text-to-speech, audio generation, and audio conversion AI models.

  • Project
    dbccccccc/ttsfm

    An OpenAI-compatible text-to-speech API service and Python SDK that converts text to natural speech using the openai.fm backend.

  • Project
    Xerophayze/TTS-Story

    A web-based multi-voice text-to-speech application for creating narrated stories and audiobooks using local and cloud TTS engines.

  • Project
    jamiepine/voicebox

    An open-source, local-first AI voice studio for voice cloning, speech generation, and system-wide dictation, featuring an MCP server for AI agent integration.