Chinese company Kling has released Video Model 3.0. The new model is described as an “all-in-one creative engine” for multimodal production. Key features include improved text and element consistency, video production with 15-second clips and greater control, customizable multi-shot recording, and more. Audio features now support multiple character references along with additional languages and accents. When it comes to image production, Kling 3.0 offers 4K output, a new continuous shooting mode, and what the company calls “more cinematic visuals.”
Ultra subscribers have exclusive early access through the Kling AI website. Official details regarding general release, API access, and technical documentation are not yet available. The Kling team published a paper on the Kling Omni model in December 2025. YouTube channel ‘Theoretally Media’ gained early access and published a detailed first impression video. The model will be rolled out to other subscription levels within a week, the channel said.
AI News Without the Hype – Curated by Humans
as The Decoder Subscriberyou can read without ads. Weekly AI Newsletterexclusive “AI Radar” Frontier Report 6 times a yearaccess to comments, and Complete archive.
Subscribe now
