Kling AI 发布 4.0 版本，支持立体音频和多语言唇形同步

kling ai released version 4.0 with several upgrades including stereo audio, multilingual lip sync, and a fast flash variant. the update allows users to generate up to 30 seconds of video in a single pass and accept up to ten keyframe images as input to pin down scene transitions, character states, and story beats. prompt comprehension has been expanded to 8,000 tokens and the upgraded 'omni reference' system accepts up to 15 reference assets in a single generation. this update affects users of ai video generation tools and signals progress in the field.