Back to Eliza

Video Generation

packages/cloud-frontend/content/video-generation.mdx

2.0.14.2 KB
Original Source

import { Callout, Tabs, Cards } from "@/docs/components";

Video Generation

Create AI-generated videos from text prompts.

<div className="status-badge status-stable">Stable</div>

Overview

elizaOS Cloud provides video generation through the configured video provider catalog. See the Video API reference or API Explorer for current models and defaults.

Quick Start

Dashboard

Navigate to Dashboard → Videos for the visual interface.

API

<Tabs items={['cURL', 'JavaScript', 'Python']}> <Tabs.Tab>

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 emerging from a cocoon in slow motion",
    "model": "fal-ai/veo3"
  }'

</Tabs.Tab> <Tabs.Tab>

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 emerging from a cocoon in slow motion',
    model: 'fal-ai/veo3',
  }),
});

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

</Tabs.Tab> <Tabs.Tab>

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 emerging from a cocoon in slow motion',
        'model': 'fal-ai/veo3',
    },
)

result = response.json()
print(result['video']['url'])

</Tabs.Tab> </Tabs>

Response

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

Available Models

Model availability and defaults are documented in the canonical Video API reference. Use that page or the API Explorer for the current model catalog and pricing-sensitive defaults.

Request Parameters

ParameterTypeRequiredDescription
promptstringText description of the video
modelstringModel to use (default: fal-ai/veo3)

Prompt Tips

Camera Movements

Include camera direction for dynamic videos:

  • camera pan left/right - Horizontal movement
  • zoom in/out - Focal adjustment
  • dolly forward/backward - Physical camera movement
  • tracking shot - Following subject
  • aerial view - Bird's eye perspective

Scene Description

Be specific about motion and timing:

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

Style Modifiers

  • slow motion - Dramatic effect
  • timelapse - Accelerated time
  • cinematic - Movie-like quality
  • handheld - Organic movement
  • steady cam - Smooth, professional

Best Practices

  1. Be specific about motion: Describe what moves and how
  2. Include timing cues: Slow motion, timelapse, etc.
  3. Specify camera work: Pan, zoom, tracking shots
  4. Set the mood: Cinematic, documentary, etc.
<Callout type="info"> Video generation typically takes 30-180 seconds depending on model and complexity. </Callout>

Error Handling

CodeErrorSolution
400Invalid promptEnsure prompt is non-empty
400Invalid modelUse a supported model
402Insufficient creditsAdd credits to your account
429Rate limitedWait and retry
500Generation failedRetry or try a different model

Next Steps

<Cards> <Cards.Card title="API Reference" href="/docs/api/video"> Complete API documentation </Cards.Card> <Cards.Card title="Gallery" href="/docs/gallery"> View and manage your videos </Cards.Card> <Cards.Card title="Image Generation" href="/docs/image-generation"> Generate images from text </Cards.Card> </Cards>