Kling AI Models
Explore Kuaishou's Kling AI family—from text and image-led video to native audio, motion control and unified multimodal creation in the 3.0 series.
Family overview
Text-to-video and image-to-video
Native audio in newer generations
Motion and shot-level control
Developed by Kuaishou
Kling overview
What is Kling AI?
Kuaishou's generative media platform for video, image, sound and effects.
Kling video models support prompt-directed motion, image animation and increasingly complete production workflows that combine understanding, generation and editing.
The 3.0 series moves toward a native multimodal architecture. Available features differ across VIDEO 3.0, Omni and Motion Control products and must not be combined into one generic endpoint claim.
Capabilities
Core Kling workflow directions
Specific availability varies by generation and product.
Evolution guide
The Kling model generations
Each generation expands the production workflow.
| Generation | Family role | Summary |
|---|---|---|
| Kling 1.x | Foundation | Established text-to-video, image-to-video and controllable motion workflows. |
| Kling 2.x | Production expansion | Improved quality and control; 2.6 added simultaneous audio-video and motion control. |
| Kling 3.0 | Native multimodal series | Combines understanding, generation and editing across text, image, audio and video. |
Workflows
A broader production family
Use cases
Where Kling can fit
Kling FAQ
Common questions
Who developed Kling AI?
Kling AI was developed by Kuaishou.
Is Kling only a video model?
No. The current platform also includes image, sound, effects and Omni tools.
Does Kling generate audio?
Kling 2.6 introduced simultaneous audio-video generation and 3.0 promotes upgraded native audio.
What is Kling Omni?
Omni is a unified multimodal product line whose capabilities should not be assigned to the standard VIDEO model by default.
Explore Kling 3.0
Understand the standard, Omni and Motion Control boundaries before access opens.