# duixcom/Duix-Avatar

🚀 Truly open-source AI avatar(digital human) toolkit for offline video generation and digital human cloning.

Repository: https://github.com/duixcom/Duix-Avatar
Canonical: https://ross.abutalabs.com/products/duix-avatar
Homepage: https://www.duix.com/
Language: C
License: NOASSERTION
License Family: other
Topics: ai-avatar, ai-avatars, digital-human, video-generation, cloning, cloning-tool, multimodal-ai, video-synthesis
Last push: 2026-04-21T07:06:36+00:00

## Health v2 (maintenance only)
Score: 57/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 78, release rhythm 38, longevity 44
- inputs: {"age_days": 617, "days_push": 134, "days_rel": 339, "gap_med": 44, "n_releases_24m": 2}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 14871, forks 2511 (observed 2026-08-28T04:11:08.821322+00:00)

## What it is
Duix.Avatar is an open-source AI avatar toolkit for offline video generation and digital human cloning, capable of cloning a person's appearance and voice from real video data. It drives virtual avatars via text or voice input to synthesize realistic talking-head videos without requiring an internet connection.

## Use cases
- generate talking-head videos from text offline
- clone my face and voice into a digital human
- create AI avatar videos without uploading data to the cloud
- build a virtual presenter driven by voice input
- produce personalized avatar videos for education or marketing
- run a local digital human video synthesis pipeline

## When to choose
- you need fully offline video synthesis for privacy
- you want to clone a real person's appearance and voice from video
- you need text- or voice-driven avatar video generation at zero cost
- you want an open-source alternative to commercial digital human platforms

## When to avoid
- you need real-time conversational avatars with cloud APIs and SDKs (use the commercial Duix platform instead)
- you need Linux or macOS support, since the offline tool targets Windows
- you require a permissively licensed library you can embed in proprietary products, as the license is non-standard
- you only need simple text-to-speech without a visual avatar

## Facets
- artifact type: application
- maturity: active
- function: video-processing, tts, speech-recognition, machine-learning, nlp, computer-vision
- domain: artificial-intelligence, computer-vision, media
- platform: windows, cross-platform
- tags: ai-avatar, digital-human, face-cloning, voice-cloning, video-synthesis, offline-generation, talking-head, video, natural-language-processing

## Member repositories
- duixcom/Duix-Avatar (main) score 57

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:08.821322+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:07:01.219346+00:00, confidence not recorded.
  - readme: https://github.com/duixcom/Duix-Avatar (fetched 2026-08-28T04:11:08.821322+00:00, sha 5d59e3b74ddf)
  - homepage: https://www.duix.com/ (fetched 2026-08-29T08:05:05.569275+00:00, sha fdf491e5c348)
  - site_page: https://docs.duix.com/documentation/introduction (fetched 2026-08-29T08:05:05.578675+00:00, sha 1f7c3ae39895)
  - site_page: https://www.duix.com/about (fetched 2026-08-29T08:05:05.582365+00:00, sha bef120c24c70)
  - site_page: https://www.duix.com/pricing (fetched 2026-08-29T08:05:05.580575+00:00, sha 720838b1d7d9)
- Data as of 2026-08-30T08:39:29.467469+00:00.