elizaos--eliza/packages/docs/cloud/api/video.mdx

---
title: Video Generation
description: Generate videos from text prompts using elizaOS Cloud.
---

# Video Generation

Generate AI-powered videos from text descriptions using the configured video
model catalog.

## Generate Video

<div className="api-endpoint">
  <span className="method-badge method-badge-post">POST</span>
  <span className="path">/api/v1/generate-video</span>
</div>

Create videos from text prompts.

### Request

<Tabs>
  <Tab title="cURL">

```bash
curl -X POST "https://elizacloud.ai/api/v1/generate-video" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A butterfly flying through a colorful garden",
    "model": "fal-ai/veo3"
  }'
```
  </Tab>
  <Tab title="JavaScript">

```javascript
const response = await fetch('https://elizacloud.ai/api/v1/generate-video', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    prompt: 'A butterfly flying through a colorful garden',
    model: 'fal-ai/veo3',
  }),
});

const data = await response.json();
console.log(data.video.url);

```
  </Tab>
  <Tab title="Python">

```python
import requests

response = requests.post(
    'https://elizacloud.ai/api/v1/generate-video',
    headers={
        'Authorization': 'Bearer YOUR_API_KEY',
        'Content-Type': 'application/json',
    },
    json={
        'prompt': 'A butterfly flying through a colorful garden',
        'model': 'fal-ai/veo3',
    }
)

data = response.json()
print(data['video']['url'])
```
  </Tab>
</Tabs>

### Parameters

| Parameter | Type   | Required | Description                          |
| --------- | ------ | -------- | ------------------------------------ |
| `prompt`  | string | ✓        | Description of the video to generate |
| `model`   | string |          | Model to use. Check the API Explorer for the current default. |

### Response

```json
{
  "success": true,
  "video": {
    "url": "https://your-storage.vercel-storage.com/videos/abc123.mp4"
  },
  "model": "fal-ai/veo3"
}
```

---

## Available Models

Model availability changes with provider catalogs and deployment configuration.
Use `/api/v1/models`, the API Explorer, or the generated OpenAPI reference for
the current video model list.

<Info>
  Video pricing is model-specific and refreshed from fal provider pages. Default
  request costs vary materially by model; inspect the API Explorer or pricing
  summary endpoint for current ranges.
</Info>

---

## Prompt Tips

### Camera Movements

Include camera direction in prompts:

- `camera pan left/right`
- `zoom in/out`
- `dolly forward/backward`
- `tracking shot`
- `aerial view`

### Scene Description

Be specific about the scene:

```json
{
  "prompt": "A golden retriever running through autumn leaves in a park, slow motion, cinematic lighting, tracking shot following the dog"
}
```

<Info>
  Video generation typically takes 30-180 seconds depending on model and
  complexity.
</Info>

---

## Error Handling

| Code | Error                | Solution                                  |
| ---- | -------------------- | ----------------------------------------- |
| 400  | Invalid prompt       | Check prompt is non-empty string          |
| 400  | Invalid model        | Use a supported model from the list above |
| 402  | Insufficient credits | Add credits to your account               |
| 429  | Rate limited         | Wait and retry with exponential backoff   |
| 500  | Generation failed    | Retry, or try a different model           |