QR codes, barcodes, stamps and logos come out as gibberish — crop to just the text area for the cleanest read.
Image to Text is a free optical character recognition (OCR) tool that pulls the words out of a picture — a photo of a page, a scanned document, a receipt, a slide, or a screenshot you paste straight in. Recognition runs entirely in your browser using the open-source Tesseract engine, so the image is never uploaded to a server. The first time you use a language it downloads a small trained data file (a few megabytes) and caches it, so later runs start instantly. Pick the language that matches the text, extract, then edit the result before copying it or saving it as a .txt file.
No. The OCR engine and the language data run inside your browser tab. The picture never leaves your device.
JPEG, PNG, WebP, GIF and BMP. You can also paste a screenshot from your clipboard with Ctrl+V or ⌘+V, and add several images at once.
OCR accuracy depends on resolution, contrast, font and skew. A sharp, straight, high-contrast image of printed text works best. For faint scans or photos, try the "Boost contrast" option.
Not reliably. The engine is trained on printed and typeset text, so handwritten notes usually come out garbled.
The engine tries to read every part of the image as text, so QR codes, barcodes, stamps and logos turn into noise. Crop the image down to just the text you want before extracting.
English, Spanish, French, German, Italian, Portuguese, Dutch, Hindi, Chinese (Simplified), Japanese, Korean, Arabic and Russian, plus common bilingual combinations including English + Hindi. Choose the one that matches your image before extracting — a document with two scripts needs the matching combination, not just one language.
Not directly. Convert the PDF pages to images first with the PDF Playground, then run them through here.