# sync.so Avatar (Image to Video)

> Video AI Model by Sync — available on Layer

Turns a single still image into a talking character lip-synced to a voice track.

sync.so Avatar (image-to-video) turns a single still into a talking character, working with any illustration or animated frame paired with a voice track. Provide a source image and an audio clip, and it animates the face to lip-sync to the audio — the output length follows the audio duration. Ideal for virtual presenters, animated avatars, and narrated character content from a single image.

## Specifications

| Property | Value |
|----------|-------|
| Provider | Sync |
| Category | Video |
| Price | 5.3 / second per second |

## Capabilities

- Lip Sync

---

[Try sync.so Avatar (Image to Video)](https://next.app.layer.ai/me/session/new?baseModelId=SYNC_LIPSYNC_V3_IMAGE_TO_VIDEO) | [All Video Models](https://layer.ai/models/video) | [All Models](https://layer.ai/models)