# MeiGen-AI/InfiniteTalk

​​Unlimited-length talking video generation​​ that supports image-to-video and video-to-video generation

Repository: https://github.com/MeiGen-AI/InfiniteTalk
Canonical: https://ross.abutalabs.com/products/infinitetalk
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-05-22T02:35:51+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 83, release rhythm 35, longevity 27
- inputs: {"age_days": 385, "days_push": 104, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7700, forks 1337 (observed 2026-08-28T04:10:02.492295+00:00)

## What it is
InfiniteTalk is an open-source model and framework for unlimited-length audio-driven talking video generation, supporting both image-to-video and video-to-video (sparse-frame video dubbing) pipelines. It is implemented in Python with pretrained weights on Hugging Face and has since been superseded by LongCat-Video-Avatar.

## Use cases
- generate talking head videos from audio
- dub a video into another language with lip sync
- animate a portrait photo to speak
- create unlimited-length talking avatar videos
- audio-driven video-to-video generation
- lip synchronization for long videos

## When to choose
- you need audio-driven talking video generation of arbitrary length
- you want to dub existing videos while preserving lip motion
- you want to animate a still image into a speaking video
- you want an open-source, Apache-2.0 alternative to closed talking-head tools

## When to avoid
- you lack a GPU or cannot run heavy diffusion model inference
- you need a polished end-user app rather than a research codebase
- you want the latest features - consider the successor LongCat-Video-Avatar instead

## Facets
- artifact type: library
- maturity: active
- function: video-processing, machine-learning, deep-learning, llm-inference
- domain: artificial-intelligence, deep-learning, media
- platform: python
- tags: talking-head-generation, audio-driven-video, lip-sync, video-dubbing, image-to-video, diffusion-models, avatar-generation, video, gpu, linux

## Member repositories
- MeiGen-AI/InfiniteTalk (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:02.492295+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 2026-08-29T17:35:27.487174+00:00, confidence not recorded.
  - readme: https://github.com/MeiGen-AI/InfiniteTalk (fetched 2026-08-28T04:10:02.492295+00:00, sha 9fb7eef9f5ab)
- Data as of 2026-08-30T08:39:29.467469+00:00.