Kuaishou Launches Kling AI 3.0 Video Model With 15-Second Clips and Native Multilingual Audio · cho.sh
Sign in to create alerts.
Kuaishou Launches Kling AI 3.0 Video Model With 15-Second Clips and Native Multilingual Audio
AI video model releases
Kuaishou Launches Kling AI 3.0 Video Model With 15-Second Clips and Native Multilingual Audio
Kling AI 3.0 launches with four variants: Video 3.0, Video 3.0 Omni, Image 3.0, and Image 3.0 Omni, unifying text, image, audio, and video into one multimodal architecture for generation and editing.
Video 3.0 extends generation length to up to 15 seconds and adds native audio in English, Chinese, Japanese, Korean, Spanish, plus multiple English accents and Chinese dialects, supporting multi-character dialogue where each speaker uses a different language.
Video 3.0 Omni builds on the prior "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 for setting duration, shot size, and camera movement per shot.
Image 3.0 Omni outputs 2K and 4K ultra-high-definition visuals aimed at professional use cases like virtual scene visualization and production assets.
Kling AI has produced more than 600 million videos for over 60 million creators and 30,000 enterprise clients since its June 2024 launch; the 3.0 models are in early access for Ultra subscribers before wider release.
cho.sh