How to use it
- Add pictures or a PDF. Drop photos, screenshots or a scanned PDF on the box, or paste a screenshot.
- Pick the language. English, Hindi, or both. The right language matters most for good results.
- Read text. Press Read text. Each page takes a few seconds.
- Download or copy. Save it as a searchable PDF, Word or text file, or copy the text.
What happens to your file
Each picture or PDF page is drawn in your browser, then Tesseract reads it line by line. For a searchable PDF the original page is kept and the recognised words are placed invisibly over the spot where they appear.
Questions
Are my files uploaded?
No. Text recognition runs inside your browser with Tesseract, the open-source OCR engine, compiled to WebAssembly. Your pictures and PDFs never leave your device.
Which languages can it read?
English and Hindi (Devanagari), separately or together in one document.
How do I get the best results?
Use a sharp, well-lit, straight picture where the text is at least as tall as normal print on a phone screen. Crop away anything that is not text. Handwriting is usually not recognised.
What is a searchable PDF?
The page looks exactly the same, but an invisible layer of the recognised text lies over it, so you can search, select and copy the words.
My PDF already has text. Do I need OCR?
No. If you can select text in the PDF, use PDF to Word or the converter instead: it reads the existing text exactly.