About this project

TTS WebUI is a comprehensive, unified web application built with Gradio and React that provides an accessible interface for a wide variety of text-to-speech (TTS), audio generation, and voice conversion models. It aims to bring together numerous state-of-the-art AI audio projects under a single, cohesive roof. ### Key Features: - **Broad Model Compatibility**: Supports popular models such as Bark, Tortoise, MusicGen, MAGNeT, Stable Audio, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS, StyleTTS2, and many more. - **Dual Interface**: Offers both a Gradio-based backend interface and a React-based frontend UI for a modern user experience. - **Extensible Architecture**: Features an integrated extension marketplace and manager, allowing users to easily install, update, and manage community extensions and custom models. - **API and Integrations**: Provides an OpenAI-compatible API, making it easy to integrate with external applications like Silly Tavern, OpenWebUI, and Text Generation WebUI. - **Multiple Installation Methods**: Supports native installers for Windows, manual setup via Python, and Docker containerization for easy self-hosting. The project is licensed under MIT, promoting open and ethical usage of generative AI technologies.