Optical character recognition (OCR) reads the words in a picture and turns them into text you can copy, edit and search. Paste a screenshot, upload a photo of a page, or drop in a scanned document.
The OCR engine (Tesseract) runs in your browser, so the image isn’t uploaded. English works offline after the first use; other languages download their dictionary the first time you pick them.
Tips for accurate results
- Use a sharp, well-lit image where the text is level and fills most of the frame.
- Screenshots give almost perfect results. Photos of paper work best taken straight on, without shadows.
- Pick the language of the text – accents and special letters are recognised much better.
Questions
Can it read handwriting?
Neat block capitals often work, but joined-up handwriting is not reliably recognised.
Does it keep the formatting?
It keeps line breaks and paragraphs, but not fonts, columns or tables.
Is my image uploaded?
No. Text recognition happens on your device.