# OmniHuman 1.5

> Video AI Model by ByteDance — available on Layer

ByteDance's latest OmniHuman, bringing a still photo to life from audio with improved motion and expression.

OmniHuman 1.5 from ByteDance is the latest generation of the audio-driven avatar model, animating a single still image of a person from an audio track. It delivers sharper lip-sync, richer emotional expression, and more natural body motion than the original, with optional text prompting and 720p or 1080p output. It is ideal for realistic digital humans in advertisements, explainer videos, and virtual communication.

## Specifications

| Property | Value |
|----------|-------|
| Provider | ByteDance |
| Category | Video |
| Price | 6.4 / second per second |

## Capabilities

- Lip Sync

---

[Try OmniHuman 1.5](https://layer.ai/me/session/new?baseModelId=OMNIHUMAN_V1_5) | [All Video Models](https://layer.ai/models/video) | [All Models](https://layer.ai/models)