Tts Webui
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!
Last verified:
What is Tts Webui?
TTS WebUI is a free, open-source Gradio-based web interface for Text-to-Speech, audio, and music generation. It allows users to generate audio from text using over 30+ AI models, including Bark, MusicGen, Tortoise, Kokoro, StyleTTS2, XTTSv2, CosyVoice, and many more, all accessible through a single unified browser interface. The tool supports both a React frontend (on port 3000) and a Gradio backend (on port 7770).
Key features include support for 600+ languages through models like Omnivoice, voice cloning capabilities via Tortoise, OpenVoice, and GPT-SoVITS, AI singing and music generation with ACE-Step and MusicGen, and over 60 community-built extensions that can be installed directly from the web UI. It offers flexible installation options including one-click installers (TTS WebUI Ignition), manual installation, Docker deployment, and Google Colab support.
TTS WebUI is designed for content creators, developers, AI enthusiasts, video producers, podasters, and anyone who wants professional voiceovers without commercial subscription costs. It is particularly valuable for users who want local, privacy-focused TTS generation, multi-language support, voice cloning, and music/audio generation all in one place. The project has over 2,600 stars on GitHub and is actively maintained with regular updates.
Tts Webui pricing
Pricing model: Freemium
TTS WebUI is completely free and open-source with no paid tiers or subscriptions. The software is licensed under MIT and available on GitHub. All features are included at no cost. Users only incur hardware costs (GPU requirements) and potential cloud GPU costs if using Runpod deployment. Model weights have different licenses (some MIT, some CC BY-NC 4.0 like MusicGen), but the WebUI itself is free. No credit systems, no usage limits, no premium plans.
Tts Webui pros
- Completely free and open-source with no subscription fees
- 30+ AI TTS models in one unified interface
- 60+ community extensions available for installation
- Supports 600+ languages via Omnivoice model
- Multiple voice cloning options (Tortoise, OpenVoice, GPT-SoVITS)
- Both React UI and Gradio Interface available
- Local installation ensures privacy and data security
- One-click installer (TTS WebUI Ignition) for easy setup
- Docker support for reproducible deployments
- Google Colab option for GPU-limited users
- AI music and singing generation with ACE-Step and MusicGen
- Regular updates with active GitHub community (2.6k stars)
- OpenAI-compatible API endpoint for integration with SillyTavern and OpenWebUI
- Voice selection from Bark Speaker Directory
- Supports Mac (M-series), AMD, Intel, and NVIDIA CUDA devices
- Audio conversion tools including RVC, Demucs, and Resemble Enhance
- No character limits or daily usage caps like commercial services
Tts Webui cons
- Large installation size (10.7 GB base plus 2-8 GB per model)
- Requires NVIDIA GPU with 6-8 GB VRAM for optimal performance
- Complex manual installation requiring Python 3.10/3.11, git, ffmpeg, NodeJS
- Some models marked as unstable or early access (CosyVoice, VibeVoice)
- pip dependency conflicts between different AI models are common
- MacOS support limited - Audiocraft only works on Linux/Windows
- Torch gets reinstalled multiple times during setup due to pip limitations
- Requires technical knowledge for troubleshooting errors and updates
Frequently asked questions about Tts Webui
What is TTS WebUI?
TTS WebUI is a free Gradio-based web interface for Text-to-Speech, audio, and music generation. It allows you to generate audio from text using over 30+ AI models including Bark, MusicGen, Tortoise, Kokoro, StyleTTS2, XTTSv2, and many more, all accessible through a single unified browser interface.
Is TTS WebUI free to use?
Yes, TTS WebUI is completely free and open-source under the MIT license. There are no subscription fees, no paid tiers, no credit systems, and no usage limits. All features are available at no cost.
What are the system requirements?
For optimal performance, you need an NVIDIA GPU with 6-8 GB VRAM and CUDA toolkit. Prerequisites include Python 3.10 or 3.11, git, ffmpeg (with vorbis support), and optionally NodeJS 22.9.0 for the React UI. The base installation is around 10.7 GB, with each model requiring an additional 2-8 GB.
How do I install TTS WebUI?
You can install via TTS WebUI Ignition ( easiest one-click installer), One-Click Legacy Installer for Windows, manual installation by cloning the repository and running pip install, Docker deployment, or Google Colab. The Ignition launcher automatically downloads and sets up everything required.
What languages are supported?
TTS WebUI supports English, Chinese, Japanese, and many more languages through different models. The Omnivoice extension supports 600+ languages with zero-shot voice cloning, and the MMS model supports over 1000 languages for massively multilingual speech synthesis.
Can I clone voices with TTS WebUI?
Yes, TTS WebUI offers multiple voice cloning options including Tortoise TTS, OpenVoice (v1 and v2), GPT-SoVITS, Bark Voice Clone, and Omnivoice. These enable zero-shot voice cloning where you can clone voices from audio samples.
Does it work on Mac?
Yes, TTS WebUI supports Mac (M-series chips), but with limitations. Audiocraft (MusicGen) is currently only compatible with Linux and Windows - MacOS support has not arrived yet. Other TTS models work on Mac with CPU or Apple Silicon.
How do I install extensions?
Extensions can be installed directly from the web UI through the Extension Manager, or via React UI. After installing or updating an extension, you need to restart the app to load it. There are 60+ extensions available including Kokoro, ACE-Step, RVC, Stable Audio, and many more.
Can I use TTS WebUI with SillyTavern or OpenWebUI?
Yes, by installing the OpenAI TTS API extension (Kokoro TTS API), you get an OpenAI-compatible endpoint at http://localhost:7778/v1/audio/speech that works with SillyTavern, OpenWebUI, and other OpenAI-compatible clients.
What ports does TTS WebUI use?
TTS WebUI runs on two ports: the React UI is accessible at http://localhost:3000 and the Gradio Interface is at http://localhost:7770. For Docker deployments, these correspond to UI_PORT (3000) and TTS_PORT (7770) environment variables.