# Audio-conditioned full-body animation on Two-person audio conditioned human animation (test)

Source: [Audio-conditioned full-body animation on Two-person audio conditioned human animation (test)](<https://www.sota2.com/research/sota/audio-conditioned-full-body-animation-on-two-person-audio-conditioned-human-animation-test>)

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

Data updated: 2026-03-06T07:08:18.436Z

Evaluation of models performing Audio-conditioned full-body animation using the test split of the Two-person audio conditioned human animation dataset. Performance is assessed using metrics including Sync-D, IQA, AES, and FVD.

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 | Audio-conditioned full-body animation |
| Dataset (including any stated split) | Two-person audio conditioned human animation (test) |
| Metric | Sync-D |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 6 of 6 |
| 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

- [Sync-D](<https://www.sota2.com/research/sota/audio-conditioned-full-body-animation-on-two-person-audio-conditioned-human-animation-test.md?metric=Sync-D>): Lower is better; unit: SCALAR.

- [IQA](<https://www.sota2.com/research/sota/audio-conditioned-full-body-animation-on-two-person-audio-conditioned-human-animation-test.md?metric=IQA>): Higher is better; unit: SCALAR.

- [AES](<https://www.sota2.com/research/sota/audio-conditioned-full-body-animation-on-two-person-audio-conditioned-human-animation-test.md?metric=AES>): Higher is better; unit: SCALAR.

- [FVD](<https://www.sota2.com/research/sota/audio-conditioned-full-body-animation-on-two-person-audio-conditioned-human-animation-test.md?metric=FVD>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Sync-D | Result date | Report paper |
| --- | --- | --- | --- |
| InterActHuman | 6.67 | Not recorded | 68fa79651e209131cea7d6a3 |
| OmniHuman | 7.068 | Not recorded | 68fa79651e209131cea7d6a3 |
| MultiTalk | 7.671 | Not recorded | 68fa79651e209131cea7d6a3 |
| Kling | 8.401 | Not recorded | 68fa79651e209131cea7d6a3 |
| CyberHost | 8.974 | Not recorded | 68fa79651e209131cea7d6a3 |
| OmniHuman | 9.482 | Not recorded | 68fa79651e209131cea7d6a3 |

### InterActHuman

Sync-D: 6.67. Result ID: 69aa7c976dbb7075b953bbcd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79651e209131cea7d6a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79651e209131cea7d6a3.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### OmniHuman

Sync-D: 7.068. Result ID: 69aa7c976dbb7075b953bbcc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79651e209131cea7d6a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79b81e209131cea7f176.md>)

Recorded evaluation configuration: {"Masking strategy":"fixed mask"}. This record does not assert independent reproduction.

### MultiTalk

Sync-D: 7.671. Result ID: 69aa7c976dbb7075b953bbca.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79651e209131cea7d6a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77de1e209131cea75ad4.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Kling

Sync-D: 8.401. Result ID: 69aa7c976dbb7075b953bbc9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79651e209131cea7d6a3.md>)

Recorded evaluation configuration: {"Version":"1.6","Lip-sync":"True"}. This record does not assert independent reproduction.

### CyberHost

Sync-D: 8.974. Result ID: 69aa7c976dbb7075b953bbc8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79651e209131cea7d6a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77de1e209131cea75ad4.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### OmniHuman

Sync-D: 9.482. Result ID: 69aa7c976dbb7075b953bbcb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79651e209131cea7d6a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79b81e209131cea7f176.md>)

Recorded evaluation configuration: {"Masking strategy":"without mask"}. This record does not assert independent reproduction.

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