Grok Imagine Video Text to Video

Grok Imagine Video by xAI - generate cinematic videos from text descriptions with AI. Create high-quality video content with natural motion, camera control, and optional audio generation.
xai/grok-imagine-video/text-to-video

Grok Imagine Video by xAI - generate cinematic videos from text descriptions with AI. Create high-quality video content with natural motion, camera control, and optional audio generation.

Try the model

Playground

Open playground
Input
Text description of the desired video.
Additional Settings More

Customize your input with more control.

Resolution of the output video. Allowed values: 480p, 720p.
115
Video duration in seconds. Range: 1 to 15.
The aspect ratio of the generated image. Allowed values: 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16.
Result
Example
  1. What would you like to do next?

    Open original

Saved example result. No new generation was requested.

Displayed run estimate: $0.3. Final charges follow the model’s billing rules below.

Grok Imagine Video Text to Video

Grok Imagine Video turns a prompt into a 1–15 second clip with native audio.

Fields

FieldTypeDefaultNotes
promptstring, required—Up to 4,096 characters.
resolution480p / 720p720pSets the per-second rate.
durationinteger 1–156Output length in seconds.
aspect_ratio16:9 / 4:3 / 3:2 / 1:1 / 2:3 / 3:4 / 9:1616:9Output frame shape.

Billing

$0.05 per output second.

OutputPrice
6s (default)$0.30
10s$0.50
15s$0.75

Failed runs are not charged.

Prompting

  • Describe subject, action, camera, and sound.

Also on SandBase

Other Grok Imagine Video endpoints: xai/grok-imagine-video/image-to-video, xai/grok-imagine-video/reference-to-video, xai/grok-imagine-video/video-edit, xai/grok-imagine-video/video-extend, xai/grok-imagine-video/1.5/text-to-video (1.5, newer).