Grok Imagine is xAI's video generation model. It creates video clips from text prompts and images with motion, generated audio, and lip-sync, available through Vercel AI Gateway.
import { experimental_generateVideo as generateVideo } from 'ai';
const result = await generateVideo({ model: 'xai/grok-imagine-video', prompt: 'A serene mountain lake at sunrise.'});Grok Imagine is xAI's video generation model, released January 28, 2026 and available through Vercel AI Gateway. It generates video clips from text descriptions and static images with motion, instruction following, and support for complex prompts and follow-up instructions to refine scenes.
The model supports three primary generation modes: text-to-video (creating clips from text descriptions), image-to-video (generating motion from static images), and video editing (modifying existing video content through style changes, object replacement, and scene alterations). It also generates audio timed to the video with lip-sync, so you can skip separate voice recording for many workflows. Grok Imagine produces short clips quickly enough for iterative creative workflows. You can call it from the AI SDK's generateVideo function, the AI Gateway playground at https://ai-sdk.dev/playground/xai:grok-imagine-video, or the v0 Grok Creative Studio. Video generation is currently available to Pro and Enterprise plan subscribers and paid AI Gateway users.