Visionati Image Scanner Autor: zquestz

Right-click any image on the web. Get AI-powered descriptions, alt text, tags, and content screening in seconds.

Visionati Image Scanner sends images to the Visionati API, where multiple AI models analyze them and return results directly in your browser. Pick from models by Anthropic, Google, OpenAI, xAI, and others.

What it does:

• Right-click any JPEG, PNG, GIF, or WebP image and select "Scan with Visionati"
• Get AI-generated descriptions, object tags, and NSFW detection in a popup
• Generate alt text for accessibility with the dedicated Alt Text role
• Choose from 12 built-in roles to shape the output: Alt Text, Artist, Caption, Comedian, Critic, Ecommerce, General, Inspector, Promoter, Prompt, Realtor, and Tweet
• Write custom prompts for full control over what the AI focuses on
• Output in 160+ languages
• Browse past scans with navigable history (configurable up to 50 entries)

Who it's for:

• Web developers and content creators who need alt text for accessibility
• Marketers generating captions and product descriptions from images
• Anyone curious about what AI sees in an image

Setup:

1. Install the extension
2. Open Settings and enter your Visionati API key (sign up at api.visionati.com)
3. Pick your AI models, role, and language
4. Right-click an image and scan

Images are processed securely via the Visionati API. The extension never sends data anywhere else.

Note: The "Automatically open popup after scan" option is not supported in Firefox. Click the extension icon to view results after scanning.

Requires a Visionati API account. Sign up and purchase credits at api.visionati.com.