Kling 4.0 adds 30-second clips and stereo audio

Kling AI's 4.0 update arrives with a set of input and output limits that are markedly higher than what the company previously offered, though it does not frame the release as a direct comparison. The system now accepts up to ten keyframe images to pin down scene transitions and story beats, and its prompt comprehension has been expanded to 8,000 tokens. The upgraded "Omni Reference" system goes further, accepting up to 15 reference assets in a single generation, including up to 10 images, 5 videos with a combined maximum of 30 seconds, and 7 elements. Kling AI says storyboards, wireframes, image grids, white-model videos, and depth-map videos all work as references.

A separate "Creative Recreation" feature lets users take existing videos as templates and swap out products or characters. According to the company, individual elements like facial expressions, body movements, camera angles, or backgrounds can be tweaked without affecting the rest of the clip. The update also adds two-channel stereo audio and improved lip sync across more than ten languages, including German, English, Japanese, Korean, and Spanish, along with various dialects and accents. In-video text generation now works in multiple languages too and stays stable during camera movements.

Alongside the main model, Kling AI is shipping a lighter Flash variant designed for faster generation at lower cost, though it tops out at 720p and 20 seconds of video. The creation interface has been redesigned, and Kling 4.0 can now be accessed through MCP and CLI, which makes it possible to build automated workflows with AI agents. Pricing for the Kling 4.0 API hasn't been announced yet, with support listed as "coming soon."