Roadmap

Available On Release

Image Capture from Screen Region

Click the tray icon, then use the primary mouse button to select any screen region and copy it directly to the clipboard as an image - no file saving or setup required.
OCR Capture from Screen Region

Click the tray icon, then use the secondary mouse button to select any screen region and copy it directly to the clipboard as plain text - no file saving or setup required.
Fullscreen Capture

Press CTRL+ALT+SHIFT+A to capture a fullscreen image or CTRL+ALT+SHIFT+S to capture the readable text using OCR on the active monitor. This is ideal for working with fullscreen applications.
QR Code Recognition

Automatically detect and decode QR codes from screen region captures, copying the decoded content directly to your clipboard as text. Great for links and other embedded info in documents. Visit the help page for information about supported formats.
Offline, Local Processing

All image capture and text recognition happens locally on your machine. No data is sent anywhere. Privacy is a core design principle.

Text-to-Speech

Have recognized text read aloud using your system’s voice engine. Useful for accessibility, multitasking, or reviewing text hands-free.
Tray Menu Icons

The tray menu will be updated to use icons instead of text labels for capture modes. We may also include previews or short descriptions of recent actions.
Improved Fullscreen Region Selection

We’re working to support region-based overlays even in fullscreen applications, matching the experience of standard windowed capture.
Hotkey Customization

We’re looking into adding customizable hotkeys for full screen capture and the capture overlay, with the Pro version also supporting history restores via hotkeys.

Automatic Language and Text Type Detection

Support for additional languages is planned, including auto-detection of source language support for additional character and text types.
Translation Support

We are looking into adding features that may allow you to translate the text captured through OCR into your system’s default language or a selected language of your choice. All processing remains fully offline for maximum privacy.
Tesseract Customization

A possible advanced version of UnicornOCR will offer a user interface for configuring Tesseract’s numerous OCR options, enabling better performance for specific layouts, use cases, or input types.
Deep Learning Enhancements

Experimentation is ongoing in using machine learning rather than traditional OCR methods to improve performance with unusual, or visually complex text. While straight forward to do in general, maintaining UnicornOCR's offline only approach makes this a challening problem to solve while maintaining performance.

Note: Some planned features may be included in the Free version, others may be part of Pro. Final availability is still being determined.

Have a suggestion? Let us know!