What happened
xAI moved Grok Imagine Video 1.5 out of API preview to general availability on June 16, and rolled out a faster Video 1.5 Fast variant on grok.com/imagine and its iOS and Android apps. The image-to-video models improve motion, physics and audio, generating ambience, sound and dialogue in a single pass. The model is available in the xAI API as grok-imagine-video-1.5.
Video 1.5 Fast produces six-second 720p clips in about 25 seconds, down from 40 or more. xAI also shipped new Projects, a 'multiple agents' feature that runs several generations in parallel, and library search, rounding out the release beyond the core model update.
Why it matters
Generating audio in the same pass as video removes a separate step that creators otherwise handle manually. Faster generation and parallel runs shorten the loop between idea and result, which matters for iterative creative work.
General availability in the API also opens the models to developers building on top of them rather than just end users.
MintedBrain take
Speed and single-pass audio are genuinely useful, but generated video still needs review for physics glitches, artifacts and rights concerns before publishing. Treat these tools as a fast first draft, and keep a human in the loop on anything customer-facing.
Discussion
Sign in to comment. Your account must be at least 1 day old.