Model · Kuaishou · Video-Gen
Kling 3.0
Kuaishou's video generation model. 3.0 adds native audio, multimodal input, and up to 15-second clips; strong on human motion and physical realism.
- Modality
- Video-Gen
- License
- Proprietary (Proprietary)
- Released
- February 5, 2026
- Last verified
- June 8, 2026
- Runs locally
- No
Strengths
- Strong human motion and facial expression
- Native audio and multimodal input (3.0)
- Image-to-video with strong identity preservation
Weaknesses
- Chinese-language-first product UX (English available)
- Closed weights
Try it
| Where | Type | Notes |
|---|---|---|
| Kling | product | Free tier |
| Replicate | hosted | API key required |
Official sources
- Product site vendor
Change log
- — Updated from Kling 2.0 to Kling 3.0 (released 2026-02-05): native audio, multimodal input, up to 15s clips. (Interim: 2.1, 2.5 Turbo, 2.6.)
- — Initial entry.
Esc