Kling AI will soon release new Video 2.6 model

Kling AI appears to be preparing a 2.6 release that will incorporate native audio directly into the video model. Internal references mention support for dialogue, songs, and sound effects under the tagline “See the sound, hear the visuals,” suggesting that videos will be accompanied by soundtracks generated in the same path as the visuals, rather than relying on separate tools or manual editing.

This release is significant as it puts Kling 2.6 Pro in a competitive position against other leading AI video models such as Sora 2 and Veo 3.1 by offering a complete multimodal workflow (video + audio + image to video) with global market audio support and high production quality.

From version 1.6 to 2.5, the Kling family has steadily improved visual fidelity and control, moving from Turbo, Pro, and Master levels. For creators and studios using Kling 2.5 and Kling Omni through third-party platforms, Kling 2.6 Pro will roll out with English and Chinese audio built-in, closing a long-standing gap with rivals that already bundle audio and atmosphere. It also builds on previous work that brought real-time audio generation to the broader Kling ecosystem.

The timing coincides with the Kling Omni Launch Week, owned by Chinese short video giant Kuaishou, which promises to release new releases over five days starting December 1st, making an announcement around December 3rd within that period plausible. With the Kling O1 positioned as a multimodal hub for text, images, and video creation, the 2.6 audio upgrade fits in as the sound layer of that stack, likely appearing first within Kling’s web tools and partner integrations, with broader availability depending on how launch week plays out.