Kling Releases Kling 4.0 Video Model
Understand the story
Kling AI released the Kling 4.0 video generation model. The new model can generate videos of up to 30 seconds in a single run, supports accepting up to 10 keyframe images at once, extends prompt understanding to 8,000 tokens, and its Omni Reference feature supports up to 15 reference assets. In addition, Kling 4.0 adds dual-channel stereo audio output and lip synchronization in over ten languages, alongside the launch of a lightweight version, Kling 4.0 Flash. Coverage of the event is mainly The Decoder's release report; there is no news yet on user feedback or market performance.
AI overview of reporting · Updated 2 h前
Reporting timeline
Explore different aspects of the story through its reporting.
- The DecoderKling AI drops version 4.0 with stereo audio, multilingual lip sync, and a lighter Flash variant
Kling AI has released Kling 4.0, which generates videos up to 30 seconds in a single run, accepts up to 10 keyframe images, extends prompt understanding to 8,000 tokens, supports up to 15 reference assets via Omni Reference, and adds dual-channel stereo audio plus lip sync in over ten languages.
Story heat trend
Not enough continuous observations to show a trend yet.