Select any region on your screen and extract text instantly with powerful OCR technology. Built for developers, researchers, and power users.
Complete setup takes less than 2 minutes
Load the extension in your browser and pin it to the toolbar for one-click access.
Go to any website, document, or visual content where text is visible. Make sure OCR Relay URL is configured in settings.
Press Alt+Shift+E to activate. Click and drag to select any text region on your screen.
Everything you need for seamless text extraction
Extract text from any screen region in seconds using your configured OCR relay endpoint.
Click and drag to select any area. Works with PDFs, images, videos, locked documents, and any visual content.
Provider secrets stay server-side in your OCR relay. RavenEye remains open source and transparent.
Instantly copy extracted text to clipboard. Auto-copy option available for faster workflow integration.
Download extracted text as .txt files with timestamps. Perfect for archiving and documentation.
Quick access with Alt+Shift+E. You can also customize shortcuts in browser extension settings.
You only need an OCR relay URL. Provider API credentials should stay on the relay server.
No provider key should be stored in the extension. Configure only the relay URL in settings.
RavenEye captures what's visible on your screen, so it works with any format: PDFs, images (JPG, PNG, WebP), videos, locked documents, scanned files, and even text rendered in canvas or WebGL.
OCR accuracy depends on image quality. For clear, high-resolution text, accuracy is typically 95%+. For best results, capture at higher zoom levels and ensure good contrast between text and background.
No. OCR processing uses a cloud service endpoint, so an internet connection is required.
Language support depends on your OCR relay/provider setup. Accuracy depends on capture quality and script complexity.
Effective Date: January 1, 2026
RavenEye collects minimal information necessary for functionality:
RavenEye shares data only with services necessary for core functionality:
RavenEye requires the following permissions:
RavenEye is fully open source. You can review the entire codebase, verify our privacy claims, and contribute at GitHub.
Any changes to this privacy policy will be posted on this page. Continued use of the extension after changes indicates acceptance of the updated policy.
For privacy concerns or questions, contact us through the Support section.
Need help? We're here to assist
Extension not activating?
Check if keyboard shortcut conflicts exist in edge://extensions/shortcuts. Try reassigning the shortcut if needed.
OCR request failed?
Check your relay URL, server availability, and internet connection. Some networks may block outbound OCR traffic.
OCR results are empty?
Ensure you're selecting a region with actual text. Increase zoom level for better capture quality and contrast.