#3232nd of 42 in Image and videoFor image, video and design, video and animation, voice, speech and music

duix-avatar

Offline talking-avatar video generator with voice cloning and lip-sync

Stars
16.2k
License
custom license
Last commit
Apr 2026
Last release
Sep 2025
Language
C
Stars, last 30 weeks+3,647
4 Apr 2026: 12,523 stars11 Apr 2026: 12,584 stars18 Apr 2026: 12,651 stars25 Apr 2026: 12,710 stars2 May 2026: 12,772 stars9 May 2026: 12,831 stars16 May 2026: 12,893 stars23 May 2026: 12,983 stars30 May 2026: 13,314 stars6 Jun 2026: 13,417 stars13 Jun 2026: 13,521 stars20 Jun 2026: 13,600 stars27 Jun 2026: 13,669 stars4 Jul 2026: 13,718 stars11 Jul 2026: 13,861 stars18 Jul 2026: 13,966 stars25 Jul 2026: 14,084 stars1 Aug 2026: 14,208 stars8 Aug 2026: 14,307 stars15 Aug 2026: 14,503 stars22 Aug 2026: 14,736 stars29 Aug 2026: 14,863 stars5 Sept 2026: 14,979 stars12 Sept 2026: 15,272 stars19 Sept 2026: 15,474 stars26 Sept 2026: 15,540 stars3 Oct 2026: 15,622 stars10 Oct 2026: 15,815 stars17 Oct 2026: 15,951 stars24 Oct 2026: 16,055 stars31 Oct 2026: 16,170 stars

12,523 on 4 Apr 202616,170 on 31 Oct 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

Duix.Avatar clones a person's face and voice from a short video, then renders lip-synced videos driven by text or audio. It runs as an Electron client plus Docker services for ASR (fun-asr), TTS (fish-speech-ziming) and video synthesis, all on a local NVIDIA GPU. The services expose local HTTP endpoints for voice synthesis (port 18180) and video synthesis (port 8383).

Who it is for: Creators and developers wanting local avatar video generation on an NVIDIA GPU

Ranked among open-source alternatives to HeyGen (#3 of 3).

Strengths

  • Runs fully offline; all compute is local, so no footage leaves the machine
  • Exposes local HTTP APIs for audio synthesis (18180) and video synthesis (8383)
  • Scripts supported in eight languages, including English, Chinese, Japanese and Spanish
  • Clients for Windows (installer) and Ubuntu 22.04 (AppImage); lite compose file available

Weaknesses

  • Requires an NVIDIA GPU; services will not start without one
  • Heavy setup: about 70GB of image downloads and 100GB free disk recommended
  • Non-real-time only; interactive avatars are routed to the paid duix.com service
  • Custom license: enterprises above 100,000 users or 10M USD revenue need a commercial agreement

What it needs

  • RAM ≥ 32 GB
  • GPU required
  • Compose
  • Needs Docker, NVIDIA Container Toolkit, Node.js 18, guiji2025/fun-asr, guiji2025/fish-speech-ziming, guiji2025/duix.avatar
  • Models: fun-asr, fish-speech-ziming

Quick answers

Is duix-avatar open source?

Its code is public on GitHub under its own license terms; read them before you use it at work.

Can you run duix-avatar with Docker?

Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.

Does duix-avatar need a GPU?

Yes, it needs a GPU. Plan for at least 32 GB of RAM.

Also in Image and video

See all 42
Also in Image and video
RankProjectScore
1frigateLocal NVR with realtime object detection for IP cameras37.1k starsMIT91 out of 100
2MoneyPrinterTurboGenerates short videos from a topic, with script, footage, voiceover and subtitles137.1k starsMIT87 out of 100
3ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows144.4k starsGPL-3.086 out of 100
#4InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows29k starsApache-2.083 out of 100
#5toonflow-appInfinite-canvas tool for AI short drama and comic video production20.1k starsMIT83 out of 100