OCR — Image to Text
Extract text from images, screenshots, and scanned documents. Powered by Tesseract.js — recognition runs in your browser and your image is never uploaded.
Drop an image or click to browse
PNG, JPG, BMP, WebP — or paste a screenshot (Ctrl+V / ⌘V)
Extracted Text
How it works
This tool uses Tesseract.js, a WebAssembly build of the Tesseract OCR engine, to recognize text directly in your browser. It offers the 10 languages listed (several can be combined) and works best with clear screenshots and scanned documents. The engine and language data are downloaded from a CDN on first use; your image never leaves your device.
- Upload, drop or paste an image containing text
- Select the language(s) of the text for best accuracy
- Click Extract Text — processing happens entirely on your device
- Copy or download the result