ForkFree

Video and audio

Duix-Avatar

by duixcom

Duix Avatar is a Windows tool that clones a person's face and voice so you can make talking-head videos from text or audio. It runs offline through Docker containers on your own computer.

Check the licenceNo standard licence detected. Read the licence before using it commercially.

View on GitHubProject website

Stars
16.2k
Licence
Unclear
Runs on
Your computer, with a GPU
Setup
Technical
Language
C
Age
678 days

What you can do with it

  • Clone your own appearance from video footage to create a reusable digital presenter
  • Clone your voice and turn typed scripts into spoken, lip-synced videos
  • Make videos in English, Japanese, Korean, Chinese, French, German, Arabic or Spanish

Make money with it

Offer a done-for-you talking-avatar video service to local businesses, educators or coaches who want regular video content without being on camera.

An idea, not financial advice. Check the licence before charging for anything built on it.

Ways a business could use it

  • Produce training, product explainer or social media videos from scripts without repeated filming or paying per-video fees
  • Offer multilingual spokesperson videos to clients without hiring presenters or voice actors

Can you use it commercially?

No standard licence detected. Read the licence before using it commercially.

Not legal advice. Read the project's licence file before building a product on it.

Getting it running

Install Node.js 18 and Docker, then run docker-compose up -d from the deploy folder, which downloads about 70GB of images.

Follow the official instructions in the project README.

Things to check

  • Licence is unclear (not asserted), so check terms before commercial use
  • Needs an NVIDIA graphics card and well over 100GB of free disk space
  • Large download of about 70GB
  • Cloning a real person's face and voice needs their consent, and misuse risks deepfakes
  • Main support is for Windows (plus Ubuntu 22.04)

Who's talking about it

Checked 02 Nov 2026. Summary drafted by AI from the project's README.

More in Video and audio

VoiceStudio debpalash
Worth a look

VoiceStudio is a desktop, mobile and Docker app that runs speech tools on your own device. It clones and designs voices, dubs videos, transcribes and dictates speech, and turns text into audiobooks in many languages.

Could replace ElevenLabs

94.8k stars +1527 a day AGPL-3.0
hyperframes heygen-com
Worth a look

HyperFrames is an open-source framework that turns HTML, CSS, media and animations into MP4 videos. It is designed so AI coding agents, or people using a command line, can write a page and render it as a video.

Could replace Remotion

77.4k stars +636 a day Apache-2.0
lemo-opuscar lemomo-ai
New and promising

Lemo-Opuscar is a tool for creating films using code, offering 59 pre-made styles or the ability to create your own. It is designed for use with Claude Opus 5.5 and can be installed as a plugin or cloned from GitHub.

Could replace Adobe Spark Video

10.8k stars +398 a day MIT