← All models
LatentSync is a video-to-video model that generates lip sync animations from audio using advanced algorithms for high-quality synchronization.
Details
- Accepts
- video + audio
Pricing
- Price
- 0.625 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | — | Random seed for generation. If None, a random seed will be used. |
| audio_urlrequired | string | The URL of the audio to generate the lip sync for. |
| loop_mode | — | Video loop mode when audio is longer than video. Options: pingpong, loop |
| video_urlrequired | string | The URL of the video to generate the lip sync for. |
| guidance_scale | number | Guidance scale for the model inference |
| enable_safety_checker | boolean | Authorized callers may set false to request relaxed screening. |
Output
| Field | Type | Description |
|---|---|---|
| video | — | The generated video with the lip sync. |