Loading...
Loading...
Extract text from images and PDFs using AI-powered OCR. Supports 7 languages. Runs entirely in your browser — no file uploads, completely private.
Select a photo, screenshot, or scanned document. JPG, PNG, WebP, BMP, and TIFF are all supported.
Tesseract.js — a battle-tested OCR engine — runs inside your browser and reads every word in the image.
Review the extracted text with a confidence score, then copy it to your clipboard or save it as a .txt file.
OCR (Optical Character Recognition) is technology that reads text from images. This tool uses Tesseract.js, a WebAssembly port of the Tesseract OCR engine, which runs entirely in your browser without sending any data to a server.
JPG, PNG, WebP, BMP, and TIFF files up to 10 MB. For best results, use high-contrast images with a minimum resolution of 300 DPI.
English, Spanish, French, German, Chinese (Simplified), Japanese, and Arabic. Select the language that matches your document before clicking Extract Text to get the best results.
Accuracy depends on image quality. Clearly printed text in good lighting typically achieves 90%+ confidence. Handwritten text, low-resolution scans, or decorative fonts will reduce accuracy. The confidence score shown after extraction gives you a quick quality indicator.