OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Tts Webui

TTS-WebUI is a self-hosted Gradio and React application that provides one web interface for extensions covering text-to-speech, voice conversion, audio and music generation, and audio processing.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Tts Webui — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use TTS-WebUI when you want a self-hosted workspace for several supported audio model extensions and can install the application and any models your chosen workflow needs.

Who it is for

  • People setting up a local or Docker-based interface for supported audio AI extensions.
  • Users who want to work with speech, voice conversion, music generation or audio-processing models through a shared web UI.

Documented uses

  • Generate speech using supported text-to-speech extensions.
  • Explore audio and music generation models from one interface.
  • Run voice-conversion and audio-processing extensions.
Before you choose

Requirements & limits

The repository is public and identifies the project as MIT-licensed. The documentation provides manual and Docker setup instructions.

  • The interface combines Gradio and React, with the React UI optional in the manual setup.
  • Manual installation lists Python 3.10 or 3.11, PyTorch and ffmpeg with Vorbis support; Node.js 22.9.0 is needed for the React UI.
  • The README notes a base legacy installation size of about 10.7 GB and an additional 2–8 GB per model.
  • CUDA in Docker requires NVIDIA Container Toolkit, and initial model downloads can delay the first output.
  • The project documents a range of extensions, but workflows depend on the selected extension and model.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up TTS-WebUI manually

Install the documented Python server, with the React interface as an optional next step.

Before you start

  • Git
  • Python 3.10 or 3.11; Python 3.12 is not supported
  • PyTorch
  • ffmpeg with Vorbis support
  • Node.js 22.9.0 for the optional React UI

Steps

  1. Clone the repository and change into its directory.

  2. Install dependencies with pip install -r requirements.txt.

  3. Start the server with python server.py --no-react.

  4. To build the React UI, enter react-ui, run npm install and npm run build, return to the repository directory, and run python server.py.

Expected outcome

The documented manual setup starts the server without React, or builds and starts the React UI as an additional interface.

Guide limitations

  • The guide lists Python 3.12 as unsupported.
  • The React UI requires the optional Node.js prerequisite.
Documentation 1 ↗
Source-based practical guide

Start TTS-WebUI with Docker Compose

Launch the documented Docker image and check the container's model-download status.

Before you start

  • Docker and Docker Compose
  • NVIDIA Container Toolkit when using CUDA inside Docker

Steps

  1. Pull ghcr.io/rsxdalv/tts-webui:main.

  2. Start the service with docker compose up -d.

  3. Check progress with docker logs tts-webui.

Expected outcome

The container starts with the Gradio backend and React front end; logs can show the progress of background model downloads.

Guide limitations

  • The first output may take time while models download.
  • The documented ports are 7770 for the Gradio backend and 3000 for the React front end.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
rsxdalv/TTS-WebUI · Official homepage title · retained in its source language
How we review sourcesSuggest a correction