# OmniHuman

> Video AI Model by ByteDance — available on Layer

Advanced video model bringing a still image of a person to life using audio, producing expressive videos.

OmniHuman from ByteDance is an advanced video generation model that brings a still image of a person to life using an audio file. It produces high-quality, expressive videos where the character's emotions and body language are dynamically driven by the nuances of the audio input. This makes it a powerful tool for creating realistic digital humans for use in advertisements, educational content, and virtual communication.

## Specifications

| Property | Value |
|----------|-------|
| Provider | ByteDance |
| Category | Video |
| Price | 5.6 / megapixel second |

## Capabilities

- Lip Sync

## Frequently Asked Questions

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

Generating assets on Layer requires using Creative Units. This model's current price is 5.6 / megapixel 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](https://layer.ai/me/session/new?baseModelId=OMNIHUMAN) | [All Video Models](https://layer.ai/models/video) | [All Models](https://layer.ai/models)