Find any model or tool and jump to its page.
Kling 3.0 Omni is Kuaishou's unified multimodal video model. One endpoint covers text-to-video, image-to-video with start and end frames, reference-image character lock, reference-video editing and style transfer, native audio with lip-sync, and multi-shot scripts. Write a prompt and Kling renders a clip with synced dialogue and ambient sound. Pin the opening and closing frames and let the model fill the middle. Drop in up to seven reference images and reuse the same character across shots. Attach a reference video and let Kling either edit it directly or lift the camera move and style onto a new scene. Available in Visual Sandbox alongside Seedance, Veo, and other AI video models, so you can pick the right tool for each shot in the same project.
| Tier | Details | Price |
|---|---|---|
| Standard | 720p, no audio | $0.21/s |
| Standard | 720p, with audio | $0.28/s |
| Pro | 1080p, no audio | $0.28/s |
| Pro | 1080p, with audio | $0.35/s |
| 4K | 2160p (no reference video) | $0.53/s |
Billed per second of output video. Visual Sandbox shows the exact price before you generate.