# Video Dubbing on RealWorld-LipSync

Source: [Video Dubbing on RealWorld-LipSync](<https://www.sota2.com/research/sota/video-dubbing-on-realworld-lipsync>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-05T08:57:56.972Z

Evaluation of Video Dubbing performance on the RealWorld-LipSync dataset, assessing metrics related to lip synchronization accuracy, identity preservation, timing stability, image quality, and video realism.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Video Dubbing |
| Dataset (including any stated split) | RealWorld-LipSync |
| Metric | Lip Sync Accuracy |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Lip Sync Accuracy](<https://www.sota2.com/research/sota/video-dubbing-on-realworld-lipsync.md?metric=Lip%20Sync%20Accuracy>): Higher is better; unit: SCALAR.

- [Identity Preservation](<https://www.sota2.com/research/sota/video-dubbing-on-realworld-lipsync.md?metric=Identity%20Preservation>): Higher is better; unit: SCALAR.

- [Timing Stability](<https://www.sota2.com/research/sota/video-dubbing-on-realworld-lipsync.md?metric=Timing%20Stability>): Higher is better; unit: SCALAR.

- [Image Quality](<https://www.sota2.com/research/sota/video-dubbing-on-realworld-lipsync.md?metric=Image%20Quality>): Higher is better; unit: SCALAR.

- [Video Realism](<https://www.sota2.com/research/sota/video-dubbing-on-realworld-lipsync.md?metric=Video%20Realism>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Lip Sync Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| LatentSync | 3.52 | Not recorded | 69a90e132d603e6de3e40889 |
| UniSync | 3.49 | Not recorded | 69a90e132d603e6de3e40889 |
| OmniSync | 3.37 | Not recorded | 69a90e132d603e6de3e40889 |
| MuseTalk | 2.44 | Not recorded | 69a90e132d603e6de3e40889 |

### LatentSync

Lip Sync Accuracy: 3.52. Result ID: 69a945486dbb7075b952dd46.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e132d603e6de3e40889.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa776a1e209131cea7323a.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"User Study"}. This record does not assert independent reproduction.

### UniSync

Lip Sync Accuracy: 3.49. Result ID: 69a945486dbb7075b952dd48.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e132d603e6de3e40889.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a90e132d603e6de3e40889.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"User Study"}. This record does not assert independent reproduction.

### OmniSync

Lip Sync Accuracy: 3.37. Result ID: 69a945486dbb7075b952dd47.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e132d603e6de3e40889.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b5f1e209131cea87fd2.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"User Study"}. This record does not assert independent reproduction.

### MuseTalk

Lip Sync Accuracy: 2.44. Result ID: 69a945486dbb7075b952dd45.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e132d603e6de3e40889.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a01e209131cea74751.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"User Study"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.