Kling AI releases video generation model 4.0
What happened
On 20 October 2026, Kling AI released video generation model 4.0. According to The Decoder, version 4.0 can generate videos of up to 30 seconds in a single pass and accepts up to 10 keyframe images, with prompt understanding extended to 8,000 tokens. It adds dual-channel stereo and lip sync in more than ten languages, and Omni Reference accepts up to 15 reference assets at a time. A lightweight Flash version was also launched, at up to 720p and 20 seconds. Kling 4.0 can be connected via MCP and CLI; API pricing has not been announced.
Written by AI from the reports · updated 1 h ago
Timeline
Follow the reports to see the event from each side.
- The DecoderKling AI drops version 4.0 with stereo audio, multilingual lip sync, and a lighter Flash variant
Kling AI has released version 4.0 of its video generator with support for clips up to 30 seconds, ten keyframe images as input, and prompt comprehension expanded to 8,000 tokens.
Heat of this event
Not enough continuous observations yet to draw a trend.