Skip to main content

Overview

Grok Imagine is xAI’s video generation model family. It supports text-to-video, image-to-video, and video editing with native audio generation. Available at 480p and 720p resolutions.

Quick start

Capabilities

Video editing

Edit an existing video with a text prompt. Input video is resized to max 854x480 and truncated to 8 seconds.

Native audio generation

Generate synchronized audio alongside the video:
cURL

Parameters

string
required
Text description of the video or edit to apply.
number
default:"5"
Video duration in seconds. Range: 1-15 seconds.
string
default:"16:9"
Output aspect ratio.
array
For image-to-video: [{ url: "image.jpg" }]. For video editing: [{ url: "video.mp4" }].
object
Set { "varg": { "generate_audio": true } } to enable native audio. Supports resolution: "480p" or "720p".
Video editing limits: Input video for grok-imagine-edit is resized to max 854x480 and truncated to 8 seconds. Plan accordingly.

Pricing

Tips

  • Native audio makes this model useful for ambient and atmospheric videos where sound matters.
  • Video editing is good for adding effects (weather, lighting changes) to existing footage.
  • Resolution defaults to 480p for speed. Set resolution: "720p" in provider options for higher quality.

Sora 2

Also supports video transformation via remix mode.

Seedance 2

Higher quality video editing with ByteDance’s model.

Grok Imagine Image

The image generation counterpart — cheapest image model.