# OmniHuman v2

> Video AI Model by ByteDance — available on Layer

ByteDance OmniHuman v2 animates a still photo from audio, with optional prompt control of motion and camera.

OmniHuman v2 from ByteDance animates a still image of a person so their speech, expression, and movement follow an audio track. An optional text prompt steers the scene, body motion, and camera. Audio runs from 5 to 300 seconds (wav or mp3). It is built for realistic digital humans in advertisements, explainers, and longer spoken performances.

## Specifications

| Property | Value |
|----------|-------|
| Provider | ByteDance |
| Category | Video |
| Price | 2.1 / second |

## Capabilities

- Lip Sync

## Frequently Asked Questions

### How much does OmniHuman v2 cost? Is it free?

Generating assets on Layer requires using Creative Units. This model's current price is 2.1 / second.

### How does Layer's pricing work?

There are no seat fees, feature gates, or plans on Layer. Instead, our platform uses a consumption based system with Creative Units (CUs) with a flexible monthly subscription. Every generation on Layer (image, video, 3D, or audio) consumes a Creative Unit, and you only pay for what you create.

---

[Try OmniHuman v2](https://layer.ai/me/session/new?baseModelId=OMNIHUMAN_V2) | [All Video Models](https://layer.ai/models/video) | [All Models](https://layer.ai/models)