Open Source & Free

Screenshot OCR

Capture your screen, instantly recognize text.

Download
Screenshot OCR Preview
Features

Everything you need

A powerful yet lightweight tool designed for seamless text extraction from your screen.

Quick Capture

Press a global hotkey to instantly capture any region of your screen. Fast, precise, and always ready.

Instant Recognition

Text is recognized immediately after capture. Results appear in milliseconds, ready to copy or search.

Multi-language

Supports Traditional Chinese, Simplified Chinese, English, Japanese, and Korean text recognition.

Offline Mode

Works completely offline with Tesseract.js and Windows OCR. No internet connection required.

System Tray

Runs silently in the background. Always accessible from the system tray, never in your way.

AI Powered

Leverage multiple OCR engines including Google Gemini AI and PaddleOCR for the best accuracy.

How It Works

Three simple steps

From screenshot to usable text in seconds.

1

Capture

Press Ctrl+Shift+S to capture any region of your screen.

2

Recognize

AI automatically recognizes text from your screenshot.

3

Use

Copy, search, or save results instantly.

Preview

See it in action

A clean, minimal interface that stays out of your way.

Keyboard Shortcuts

Built for speed

Access every feature without lifting your hands from the keyboard.

Shortcut Action
Ctrl + Shift + SCapture screenshot region
Ctrl + Shift + CCopy recognized text
Ctrl + Shift + GGoogle search recognized text
Ctrl + Shift + HOpen recognition history
EscCancel capture / Close window
Setup Guide

OCR engines at a glance

Most engines work out of the box. Gemini AI requires a free API key for enhanced accuracy.

Offline Engines
No Setup Needed

Tesseract.js, Windows OCR, and PaddleOCR all work offline with zero configuration. Just install and start using.

  1. Download and install Screenshot OCR
  2. Press Ctrl+Shift+S to capture
  3. Text is recognized automatically
Google Gemini AI
Optional - API Key

Gemini 2.0 Flash provides superior accuracy for artistic fonts and complex layouts. Free tier available.

  1. Visit Google AI Studio and create an API key
  2. Open Screenshot OCR Settings
  3. Paste the API key in the Gemini API Key field
  4. Click the Gemini button when recognizing to use AI
Tech Stack

Built with modern tools

Electron 28 React 18 Vite 5 TS TypeScript Tesseract.js 5 PaddleOCR Google Gemini AI
FAQ

Frequently asked questions

What languages does it support?

Supports Traditional Chinese, Simplified Chinese, English, Japanese, and Korean. Multiple languages can be recognized simultaneously.

Does it require an internet connection?

No. Tesseract.js, Windows OCR, and PaddleOCR all work completely offline. Only the optional Gemini AI feature requires internet.

Is Gemini AI free?

Yes. Google provides a free tier for Gemini API. You just need to create an API key at Google AI Studio — no credit card required.

Will my data be uploaded anywhere?

All offline OCR processing stays on your machine. If you use Gemini AI, the screenshot is sent to Google's API for recognition only — nothing is stored.

Does it support macOS or Linux?

Currently Windows only. macOS and Linux support may be added in future versions.

Is it open source?

Yes, fully open source under the MIT License. You can view, modify, and contribute to the code on GitHub.