Video Generation Quickstart

This quickstart walks you through generating your first video with AI Gateway. Supported models include Veo, Kling, Wan, and Grok Imagine Video.

1. Set up your project

   Create a new directory and initialize a Node.js project:

   Terminal

   mkdir ai-video-demo
   cd ai-video-demo
   pnpm init

2. Install dependencies

   Install AI SDK v6 and development dependencies:

   npmyarnpnpmbun

   Terminal

   npm install ai dotenv @types/node tsx typescript

   Terminal

   yarn add ai dotenv @types/node tsx typescript

   Terminal

   pnpm add ai dotenv @types/node tsx typescript

   Terminal

   bun add ai dotenv @types/node tsx typescript

3. Set up your API key

   Go to the AI Gateway API Keys page in your Vercel dashboard and click Create key to generate a new API key.

   Create a .env.local file and save your API key:

   .env.local

   AI_GATEWAY_API_KEY=your_ai_gateway_api_key

4. Generate a video

   Create an index.ts file:

   index.ts

   import { experimental_generateVideo as generateVideo } from 'ai';
   import fs from 'node:fs';
   import 'dotenv/config';
    
   async function main() {
     const result = await generateVideo({
       model: 'google/veo-3.1-generate-001',
       prompt: 'A serene mountain landscape at sunset with clouds drifting by',
       aspectRatio: '16:9',
       duration: 8,
     });
    
     // Save the generated video
     fs.writeFileSync('output.mp4', result.videos[0].uint8Array);
    
     console.log('Video saved to output.mp4');
   }
    
   main().catch(console.error);

   Run your script:

   Terminal

   pnpm tsx index.ts

   Video generation can take several minutes. If you hit timeout issues, see extending timeouts for Node.js.

   The generated video will be saved as output.mp4 in your project directory.

5. Next steps

   • See supported video generation models
   • Learn about image-to-video generation to animate images

Transform a single image into a video by adding motion. The image becomes the video content itself.

import { experimental_generateVideo as generateVideo } from 'ai';
import fs from 'node:fs';
import 'dotenv/config';
 
const result = await generateVideo({
  model: 'alibaba/wan-v2.6-i2v',
  prompt: {
    image: 'https://example.com/your-image.png',
    text: 'The scene slowly comes to life with gentle movement',
  },
  duration: 5,
});
 
fs.writeFileSync('output.mp4', result.videos[0].uint8Array);

Generate a video that transitions between a starting and ending image. The model interpolates the motion between them.

import { experimental_generateVideo as generateVideo } from 'ai';
import fs from 'node:fs';
import 'dotenv/config';
 
const firstFrame = fs.readFileSync('start.png');
const lastFrame = fs.readFileSync('end.png');
 
const result = await generateVideo({
  model: 'klingai/kling-v2.6-i2v',
  prompt: {
    image: firstFrame,
    text: 'Smooth transition between the two scenes',
  },
  providerOptions: {
    klingai: {
      imageTail: lastFrame,
      mode: 'pro',
    },
  },
});
 
fs.writeFileSync('output.mp4', result.videos[0].uint8Array);

Generate a new video scene featuring characters or content from reference media. References can be images or videos that show the model what your characters look like.

import { experimental_generateVideo as generateVideo } from 'ai';
import fs from 'node:fs';
import 'dotenv/config';
 
const result = await generateVideo({
  model: 'alibaba/wan-v2.6-r2v',
  prompt: 'character1 and character2 have a friendly conversation in a cozy cafe',
  resolution: '1920x1080',
  duration: 4,
  providerOptions: {
    alibaba: {
      // References can be images or videos
      referenceUrls: [
        'https://example.com/cat.png',
        'https://example.com/dog.png',
      ],
      shotType: 'single',
    },
  },
});
 
fs.writeFileSync('output.mp4', result.videos[0].uint8Array);

Some video models require URLs instead of raw file data for image or video inputs. You can use Vercel Blob to host your media files.

1. Go to the Vercel dashboard
2. Select your project (or create one)
3. Click Storage in the top navigation
4. Click Create Database and select Blob
5. Follow the prompts to create your blob store
6. Copy the BLOB_READ_WRITE_TOKEN to your .env.local file

AI_GATEWAY_API_KEY=your_ai_gateway_api_key
BLOB_READ_WRITE_TOKEN=your_blob_token

Install the Vercel Blob package:

pnpm add @vercel/blob

import { experimental_generateVideo as generateVideo } from 'ai';
import { put } from '@vercel/blob';
import fs from 'node:fs';
import 'dotenv/config';
 
// Upload image to Vercel Blob
const imageBuffer = fs.readFileSync('input.png');
const { url: imageUrl } = await put('input.png', imageBuffer, {
  access: 'public',
});
 
const result = await generateVideo({
  model: 'klingai/kling-v2.6-i2v',
  prompt: {
    image: imageUrl, // Pass URL instead of buffer
    text: 'The scene slowly comes to life with gentle movement',
  },
  providerOptions: {
    klingai: {
      mode: 'std',
    },
  },
});
 
fs.writeFileSync('output.mp4', result.videos[0].uint8Array);

See the Vercel Blob docs for more details on uploading and managing files.

For more details, see the Video Generation Capabilities docs.