Kuaishou Launches Kling AI 3.0 with 15-Second Native-Audio Video and Multi-Shot Storyboarding · cho.sh
Kuaishou Launches Kling AI 3.0 with 15-Second Native-Audio Video and Multi-Shot Storyboarding
AI video model releases
Kuaishou Launches Kling AI 3.0 with 15-Second Native-Audio Video and Multi-Shot Storyboarding
Kuaishou released the Kling AI 3.0 model family: Video 3.0, Video 3.0 Omni, Image 3.0, and Image 3.0 Omni, currently in early access for Ultra subscribers before a public rollout
Video 3.0 extends generation length to 15 seconds and adds native multilingual audio, producing speech in English, Chinese, Japanese, Korean, Spanish, plus various English accents and Chinese dialects, including multi-character scenes with different languages per speaker
Video 3.0 Omni builds on the "Elements" feature from Kling Video O1, letting creators upload a reference video to extract a character's visual traits and voice for reuse across scenes, and adds a multi-shot storyboard tool controlling duration, shot size, perspective, and camera movement per shot
Image 3.0 and Image 3.0 Omni now output 2K and 4K resolution, aimed at production assets and virtual scene visualization with detailed texture and lighting fidelity
Kling AI reports over 60 million creators, more than 600 million videos generated, and over 30,000 enterprise clients since its June 2024 launch
cho.sh