# 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 per second |

## Capabilities

- Lip Sync

---

[Try LatentSync](https://next.app.layer.ai/me/session/new?baseModelId=LATENTSYNC) | [All Video Models](https://layer.ai/models/video) | [All Models](https://layer.ai/models)