Kling AI announced the launch of its Kling 3.0 models on 24th Jun 2026, including Video 3.0, Video 3.0 Omni, Image 3.0 and Image 3.0 Omni. The model series features upgrades in consistency, photorealistic output, extended video duration up to 15s, and native audio generation across multiple languages, dialects, and accents. Powered by an integrated unified training framework, the series supports full multimodal input and output spanning text, images, audio, and video. The models integrate tasks including text-to-video, image-to-video, reference-to-video, and in-video editing into a single architecture. The Kling AI 3.0 models are now available for exclusive early access to Ultra subscribers. Video 3.0 enables creators to upload reference videos and multiple image references to ensure visual coherence. Its features include native audio generation for speech in English, Chinese, Japanese, Korean, Spanish, and accents such as American, British and Indian accents, as well as complex multi-character dialogue scenes. The model supports longer video generation up to 15 seconds and can handle intricate sequences with smooth transitions. Video 3.0 understands multi-scene, multi-shot instructions and can retain or generate text with high accuracy for e-commerce advertising.