SDK
sdk.describe()
Generate detailed descriptions and captions for images using AI
sdk.describe()
Generate a detailed text description, caption, or alt text for any image using CoreViz's vision models.
Interactive Demo
Try it out ↓
Signature
sdk.describe(image: string, options?: DescribeOptions): Promise<string>Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
image | string | Yes | Image URL or base64 data URI |
options.prompt | string | No | Custom prompt to guide the description (e.g. "Describe only the clothing") |
Returns
Promise<string> — the description text.
Examples
import { CoreViz } from '@coreviz/sdk';
const sdk = new CoreViz({ apiKey: process.env.COREVIZ_API_KEY });
// Basic description
const description = await sdk.describe('https://example.com/photo.jpg');
console.log(description);
// "A red sports car is parked on a cobblestone street in front of a brick building..."
// Custom prompt
const altText = await sdk.describe('https://example.com/photo.jpg', {
prompt: 'Write a short, accessible alt text for this image (under 120 characters)',
});
// From a local file (browser)
const file = event.target.files[0];
const resized = await sdk.resize(file);
const description2 = await sdk.describe(resized);Use Cases
- Accessibility — generate alt text for
<img>elements - CMS automation — auto-fill image descriptions on upload
- Social media — generate captions for posts
- Search indexing — create text metadata from visual content
Raw API Endpoint
This method calls POST /api/ai/describe. See the Vision API Reference for raw HTTP details.