What this tool does
This tool reads the text in pictures and scanned documents and gives it back to you as text you can copy, edit and search. It works with photos of letters and signs, screenshots, receipts, scanned pages and PDFs that are really just images. Add your files, pick the language, and press Read text.
Photos and screenshots
Drop in JPG, PNG, WebP, GIF or BMP images, or paste a screenshot straight from your clipboard with Ctrl+V or Cmd+V. Several files are read one after another, and their text is collected in one place.
Scanned PDFs
Some PDFs contain pictures of pages instead of real text, so nothing can be selected or copied. Add the PDF here and every page is read in turn. If a PDF already contains real text, you can usually select and copy it directly instead.
Getting the best results
- Use a clear, well-lit image where the text is in focus and not too small.
- Pick the language the text is written in, so accents and special letters come out right.
- Crop away anything that is not text, such as photos and decorations.
- Straight, printed text reads best. Handwriting is not supported.
Privacy
Your images never leave this device. The OCR engine and the language files are downloaded to your browser once, and the reading happens right here. There is no upload step and no server that sees your documents.
Questions
Which languages are supported?
English, Spanish, French, German, Portuguese, Italian, Dutch and Indonesian. More are on the way.
Why is the first read slower?
The first time you use a language, your browser downloads the engine and that language's data, a few megabytes in total. After that it is kept in your browser's cache, so later reads start straight away.
Is the text perfect?
OCR is very good on clear printed text, but it can confuse similar characters such as 0 and O, especially in small or blurry images. The text box is editable, so you can fix anything before copying.