# LatentSync

> Video AI Model by ByteDance — available on Layer

Fast, affordable video-to-video lipsync that syncs mouth motion to any audio track.

LatentSync is an open-source video-to-video lipsync model that generates lip motion synchronized to an audio track. It offers a fast, budget-friendly path to re-syncing existing footage to new speech, making it well-suited for high-volume localization and quick iterations where cost matters.

## Specifications

| Property | Value |
|----------|-------|
| Provider | ByteDance |
| Category | Video |
| Price | 0.14 / second |

## Capabilities

- Lip Sync

## Frequently Asked Questions

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

Generating assets on Layer requires using Creative Units. This model's current price is 0.14 / 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 LatentSync](https://layer.ai/me/session/new?baseModelId=LATENTSYNC) | [All Video Models](https://layer.ai/models/video) | [All Models](https://layer.ai/models)