# OpenTalker/video-retalking

[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

Repository: https://github.com/OpenTalker/video-retalking
Canonical: https://ross.abutalabs.com/products/video-retalking
Homepage: https://opentalker.github.io/video-retalking/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: lip-synchronization, talking-head-videos, video-editing, siggraph-asia-2022
Last push: 2024-08-05T05:59:59+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1449, "days_push": 758, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7280, forks 1053 (observed 2026-08-28T04:09:57.999383+00:00)

## What it is
VideoReTalking is a Python research system from SIGGRAPH Asia 2022 that edits real-world talking-head videos to match a given audio track, producing high-quality lip-synced output. It uses a three-stage pipeline of expression normalization, audio-driven lip synchronization, and identity-aware face enhancement.

## Use cases
- sync a talking head video's lips to new audio
- dub a video into another language with matching lip movement
- edit the mouth of a person in a video to say different words
- generate lip-synced talking head videos from audio
- enhance faces in synthesized talking head videos
- retime facial expressions in a video to a canonical template

## When to avoid
- you need real-time or streaming lip-sync
- you want a polished end-user application rather than a research codebase
- you lack a GPU or cannot run deep learning inference locally
- you need full-body or multi-person video editing

## Facets
- artifact type: library
- maturity: maintenance
- function: video-processing, machine-learning, deep-learning, computer-vision, audio-processing
- domain: computer-vision, deep-learning, artificial-intelligence, media
- platform: python, cross-platform
- tags: talking-head, lip-sync, face-generation, video-editing, research-code, siggraph-asia-2022, face-enhancement, video, linux, gpu

## Member repositories
- OpenTalker/video-retalking (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:57.999383+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 2026-08-29T17:38:53.267770+00:00, confidence not recorded.
  - readme: https://github.com/OpenTalker/video-retalking (fetched 2026-08-28T04:09:57.999383+00:00, sha f87ce00c5e31)
  - homepage: https://opentalker.github.io/video-retalking/ (fetched 2026-08-29T08:34:14.797380+00:00, sha 2263ab200574)
- Data as of 2026-08-30T08:39:29.467469+00:00.