Image to text (OCR)
Get the text out of a photo of a document, a screenshot, a scanned letter or a whole scanned PDF instead of typing it again. Tesseract, a well-proven open-source OCR engine, reads it right in your browser in English, German, Spanish, French, Chinese, Hindi and 10 more languages. The result appears in an editor, so you can fix a word before you copy it.
How it works
- Drop an image or a scanned PDF, or paste a screenshot with Ctrl+V.
- Pick the language of the text.
- Check the text, then copy it or download it as .txt.
FAQ
How accurate is it?
Printed text in a sharp, straight photo or scan is usually recognised almost perfectly. Handwriting, very small text, strong shadows and fancy fonts give more mistakes.
Can it read a PDF?
Yes. Scanned PDFs are read page by page. If a PDF already contains real text, you can usually just select and copy it in your PDF viewer.
Is my file uploaded?
No. Text recognition runs on your device; only the language data is downloaded once.