Kuaishou's Kling AI says Kling 4.0 is now fully available on klingai.com, moving the model from preview access to a general rollout. The update focuses on longer native clips, richer multi-reference control and audio that ships with the picture, rather than rehashing the September capability preview.
Creators can generate a single native clip of up to 30 seconds and set as many as 10 keyframes to steer character state, scene changes and plot beats. A generation job can combine up to 10 images, five video clips and seven subjects so references for character, motion, camera and sound work together. The product also supports multi-shot continuation that can extend a sequence toward about two minutes.
Audio is part of the full launch package. Kling 4.0 supports dual-channel stereo and lip sync across multiple languages and regional accents, including Chinese, English, Japanese, Korean, Spanish, Portuguese, German, French and Hindi, plus several Chinese dialects and English accent variants. Prompt input can run to about 8,000 tokens, with the system able to expand and polish instructions in a director-style pass.
Kling AI says 4K and 1080p 10-bit HDR output, plus an enterprise API, are coming soon, and that Kling 4.0 capabilities are already wired into MCP and CLI workflows for broader tooling. The company also highlights stronger camera moves, style controls and edits that add, change or remove subjects and backgrounds inside an existing clip.
The September preview already outlined the 30-second native length and multi-reference ideas; this release is the moment those features open to all users on the public site, with audio, MCP/CLI hooks and the near-term HDR and API dates as the main new commercial details.
SEE ALSO: Kling AI Previews Kling 4.0 With 30-Second Native Clips and Multi-Reference Control