Kling AI launches VIDEO 2.6 with native audio

Silent AI clips are finally getting a voice. Kling AI just released VIDEO 2.6, marking its first model equipped with native audio generation.

Instead of generating a mute video and leaving the sound design to third-party tools, VIDEO 2.6 generates video and synchronized audio in a single pass. Kling pitches the upgrade around the line "See the Sound, Hear the Visual," emphasizing coherent audiovisual storytelling. To showcase what it can do, the company teamed up with community creators to debut a short film titled "I Have a Secret."

One prompt, picture and sound

Until now, putting together an AI video clip usually meant generating footage in one app, hunting down sound effects in another, and spending time manually aligning the timeline.

VIDEO 2.6 builds that audio layer directly into the core generation process. Kling is also running a limited-time social promotion offering credits and standard plans to get creators testing the new workflow.

Why it matters

For digital creators and animators, native sound output cuts out one of the most tedious parts of AI video production. If the audio matches the on-screen action cleanly, rapid prototyping for ads and social shorts becomes much faster.

We think this launch signals an important shift in the AI video landscape: the battle is moving beyond pure visual resolution toward delivering ready-to-watch multimedia packages. Kling is smart to target this friction point early. That said, outside curated showcase films, it remains to be seen how well the model handles complex ambient audio without introducing weird artifacts or sync drift.