How to extract text from an image
- Drop an image or a scanned PDF into the box, tap to take or choose a photo on your phone, or copy a screenshot and press Ctrl+V (Cmd+V on a Mac).
- Choose the language the text is written in. For mixed text, such as English and Urdu, pick a second language too.
- Wait a few seconds. The text appears in an editable box, and the preview outlines every word it found.
- Fix any mistakes, then copy the text or download it as a .txt file.
The first time you use a language, its recognition data (2–15 MB) downloads and is then cached by your browser.
Getting the best accuracy
- Sharp and straight: hold the phone parallel to the page and tap to focus. Tilted or blurry text is the main cause of errors.
- Even light: avoid shadows across the page and glare on glossy paper.
- Big enough text: letters should be at least 20 pixels tall. Zoom in or crop to the part you need.
- Right language: the language setting matters a lot, especially for accents and non-Latin scripts.
- Printed text works best. Neat handwriting is sometimes readable, but expect mistakes.
The coloured boxes on the preview show how confident the reader was: green words are almost certainly right, orange and red ones are worth checking.
Is it a PDF with selectable text?
If you can already select text in your PDF, it isn't a scan, and PDF to Text extracts it instantly and perfectly. Use this OCR tool for scanned documents, photos of pages and PDFs where the text can't be selected. Up to 30 pages are read at a time.
Uses
- Copy a quote or paragraph from a book or printed article.
- Turn a screenshot of an error message, chat or table into text you can search and paste.
- Digitise receipts, letters and old documents.
- Get the text from a poster, sign or slide to translate it.
- Make scanned notes searchable and editable.
Private by design
Most online OCR services upload your document to their servers. Here, recognition runs inside your browser using Tesseract, an open-source OCR engine originally developed at HP and later by Google. Your images and PDFs never leave your device.
Frequently asked questions
How do I copy text from an image?
Drop the image into the tool, choose its language, and copy the extracted text from the box. You can also download it as a .txt file.
Does it work with Urdu and Arabic?
Yes. Choose Urdu, Arabic or Persian as the language. Right-to-left text is supported.
Can it read scanned PDFs?
Yes. Drop a scanned PDF and up to 30 pages are read, one after another.
Is my document uploaded?
No. The OCR runs in your browser. Only the language data is downloaded, once.
Can it read handwriting?
Neat handwriting sometimes works, but the tool is designed for printed text, so expect some errors.
Last updated October 2026 · More image tools