X AI Grok Imagine Video Text To Video

X AI Grok Imagine Video Text To Video

Playground

X-AI Grok Imagine Video generates videos from text descriptions using xAI’s Grok Imagine Video model. Create high-quality videos with customizable duration, aspect ratio, and resolution. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Grok Imagine Video Text-to-Video generates videos directly from text prompts. Describe the scene, subject, motion, camera behavior, and atmosphere, then choose duration, aspect ratio, and resolution to create a short video output.

Why Choose This?

• Text-driven video generation
  Create videos from natural-language descriptions without providing an input image or video.

• Short video duration options
  Generate 6s or 10s videos for quick creative iteration and short-form content.

• Multiple aspect ratios
  Supports 16:9, 1:1, and 9:16 for landscape, square, and vertical video formats.

• Resolution options
  Choose 720p for higher-quality output or 480p for lower-resolution output.

• Simple generation workflow
  Provide a prompt, select output settings, and generate the final video.

Parameters

How to Use

1. Write your prompt — Describe the scene, subject, motion, camera movement, lighting, and atmosphere.
2. Set duration — Choose 6 or 10 seconds.
3. Select aspect ratio — Use 16:9 for landscape, 9:16 for vertical content, or 1:1 for square video.
4. Select resolution — Use 720p for higher-quality output or 480p for lower-resolution output.
5. Run — Submit the request and retrieve the generated video.

Pricing

Pricing is $0.05 per second of generated video.

Best Use Cases

• Social media videos — Generate short-form videos for vertical, square, or landscape formats.
• Concept visualization — Turn written ideas into quick motion previews.
• Marketing and ads — Create short promotional clips from text descriptions.
• Storytelling — Generate narrative video scenes from detailed prompts.
• Creative prototyping — Test video concepts before production.

Pro Tips

• Be specific about subject, action, camera movement, lighting, and atmosphere.
• Use 16:9 for widescreen videos, 9:16 for mobile-first content, and 1:1 for square layouts.
• Use 6s for quick testing and 10s when the scene needs more time to develop.
• Choose 720p for higher-quality output and 480p when lower resolution is acceptable.
• Include motion details and timing cues for more controlled video generation.

Related Models

• Grok Imagine Video Image-to-Video — Generate video from reference images.
• Grok Imagine Video Edit — Edit existing videos with text instructions.
• Grok Imagine Image Text-to-Image — Generate images from text prompts.

## Authentication

For authentication details, please refer to the [Authentication Guide](/api-authentication).

## API Endpoints

### Submit Task & Query Result

<ApiTabs submitUrl={model.submitUrl} resultUrl={model.resultUrl} payload={model.defaultValues} />

## Parameters

### Task Submission Parameters

#### Request Parameters

<RequestParams params={model.params} />

#### Response Parameters

<SubmitResponse />

#### Result Request Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| id | string | Yes | - | Task ID |

#### Result Response Parameters

| Parameter | Type | Description |
|-----------|------|-------------|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., "success") |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array&lt;string \| object&gt; | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: `created`, `processing`, `completed`, or `failed` |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |