HeadsUpAI

Vercel adds Grok Imagine Video 1.5 with native audio generation

Vercel has added Grok Imagine Video 1.5 to its AI Gateway and AI SDK 6. The integration enables text-to-video and image-to-video workflows with native audio and lip-syncing in a single pass. Developers can invoke these capabilities through the generateVideo function, which standardizes video generation (creating video from text or image inputs) across multiple providers.
Model
xai/grok-imagine-video
Capabilities
Text-to-video, image-to-video, video editing
Audio
Native generation with lip-sync
SDK Version
AI SDK 6
Access
Pro and Enterprise plans

This addition brings the current leader of the Arena Image-to-Video leaderboard into the Vercel ecosystem. By hosting the model on its AI Gateway, Vercel allows teams to switch between providers by changing a model string. This builds on the platform's previous expansion of video generation across four providers to simplify multi-model infrastructure.

Currently in beta, the model is available for Vercel Pro and Enterprise customers and paid AI Gateway users. Beyond generation, it supports video editing for style transfers and scene transformations. Users can experiment via the AI Gateway playground or the v0 Grok Creative Studio template.

Vercel Developers
Vercel Developers
@vercel_dev
X

Grok Imagine Video 1.5 on AI Gateway. Image-to-video generation with synced audio in one pass. ๐šŠ๐š ๐šŠ๐š’๐š ๐š๐šŽ๐š—๐šŽ๐š›๐šŠ๐š๐šŽ๐š…๐š’๐š๐šŽ๐š˜({ ๐š–๐š˜๐š๐šŽ๐š•: '๐šก๐šŠ๐š’/๐š๐š›๐š˜๐š”-๐š’๐š–๐šŠ๐š๐š’๐š—๐šŽ-๐šŸ๐š’๐š๐šŽ๐š˜-๐Ÿท.๐Ÿป-๐š™๐š›๐šŽ๐šŸ๐š’๐šŽ๐š ', ๐š™๐š›๐š˜๐š–๐š™๐š: '๐šŠ ๐š›๐šŠ๐š‹๐š‹๐š’๐š ๐šœ๐š™๐š›๐š’๐š—๐š๐š’๐š—๐š https://t.co/EO02UKu0I2

54retweets461likes
View on X

Still wondering? A few quick answers below.

Vercel integrated xAI's video model into its AI Gateway and SDK, allowing developers to generate video with audio programmatically.

Developers can use the generateVideo function in AI SDK 6 or experiment with the model in the AI Gateway playground.

Yes, the model features native audio generation with natural voices and accurate lip-syncing in a single generation pass.

The model is currently in beta and available for Vercel Pro and Enterprise plans, as well as paid AI Gateway users.

Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards โ†’

Share this update