SAN FRANCISCO — xAI has pushed a major upgrade to Grok Imagine, its image-and-video generator, extending clip length to 15 seconds at high definition with native audio and vaulting the tool to the top of an independent video-generation leaderboard.
Elon Musk showcased the update on X, where the feature is built directly into the app used by hundreds of millions of people. The latest release, Grok Imagine Video 1.5, now produces 720p clips of up to 15 seconds with synchronized sound, and according to comparative rankings sits at number one on the Image-to-Video Arena. The pace of iteration follows the agent mode xAI added days earlier, which let Grok generate visuals autonomously.
Adoption at staggering scale
The clearest measure of Grok Imagine's momentum is usage. xAI reports the tool has generated more than 1.2 billion videos in the past 30 days alone, a figure that places it among the most-used AI media tools in the world. That volume is a direct benefit of distribution: Grok Imagine ships inside the Grok app and the X platform, giving it a built-in audience that standalone competitors cannot match.
Under the hood, the feature relies on xAI's proprietary Aurora model to turn text prompts into images and short video, with particular attention paid to accurate text rendering, historically a weak point for AI image tools. The move to longer clips with native audio pushes Grok from still-image novelty toward genuinely useful short-form video.





