A unified web interface for text-to-speech, voice cloning, and audio generation with support for dozens of AI models.
TTS WebUI is an open-source web application that provides a unified interface for running and experimenting with dozens of text-to-speech, voice cloning, and audio generation AI models. It solves the problem of managing multiple disparate audio AI projects by consolidating them into a single, extensible platform with a modern web UI.
AI enthusiasts, developers, and researchers working with speech synthesis, voice cloning, or audio generation who want a free, self-hosted alternative to commercial TTS services with access to cutting-edge open-source models.
Developers choose TTS WebUI because it offers an unparalleled collection of audio AI models in one place, is completely free and open-source, supports easy extension via a marketplace, and provides self-hosting capabilities with Docker and OpenAI-compatible API integration.
A single Gradio + React WebUI with extensions for ACE-Step, OmniVoice, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS, Stable Audio, MMS, StyleTTS2, MAGNet, AudioGen, MusicGen, Tortoise, RVC, Vocos, Demucs, SeamlessM4T, and Bark!
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Consolidates over 30 text-to-speech, voice cloning, and audio generation models—from Bark and Tortoise to MusicGen and RVC—in one interface, as detailed in the extensive supported models table.
Features a built-in extension marketplace and external catalog for adding new models and tools, enabling community-driven growth without modifying core code.
Offers both a modern React frontend and a classic Gradio UI, catering to different user preferences with separate ports, as shown in the installation and screenshots.
Provides an API that mimics OpenAI's TTS endpoint, allowing easy integration with AI chatbots like Silly Tavern and OpenWebUI, documented in the Integrations section.
Supports local or server deployment via Docker, manual installation, or a one-click installer, giving full control over data and model usage.
The README admits persistent 'Red messages in console' due to incompatible packages from disparate AI projects, creating a fragile environment that may break with updates.
Base installation consumes 10.7 GB, with each model adding 2-8 GB, making it prohibitive for systems with limited storage or SSD constraints.
Extensions and core updates require manual intervention via a control panel and app restarts, lacking automated management for busy deployments.
Only supports Python 3.10 or 3.11, with 3.12 unsupported, forcing users to maintain older environments and potentially hindering compatibility.