Kling 4.0: clips up to 30s with sound and lip-sync, from a prompt, frames or references (photo, video, voice).
Kling 4.0 is available in IIshki Studio — video generation from a prompt, paid for with tokens. IIshki club members get reduced prices on every model. Pick a model above, set the parameters and start the generation.
Kling 4.0 (Kling AI) is Kuaishou's next-generation video model: clips up to 30 seconds in a single pass, with native sound and lip-synced speech. It works from text, between a first and a last frame, or from references: a character photo, a video with the camera move you want and a voice recording.
Kling 4.0 makes clips up to 30 seconds in one pass, generates sound and lip-synced speech itself, and understands references: up to 10 photos, 5 videos and 3 voices you can mention in the prompt as @Image1, @Video1, @Audio1.
Yes. In References mode, upload the clip and mention it as @Video1: the model keeps the camera move, pacing and composition and swaps the character, product or background for the ones in your photos.
Choose Frames mode and upload up to 10 images in order: the first becomes the start, the last the end, the rest are in-between keyframes. Describe what happens between them. Shorter clips take fewer frames: up to 4 at 3 s, up to 10 from 9 s.