How to OCR PDF
- Select a scanned PDF.
- Choose the language of the text, such as English, Hindi or English + Hindi, and the pages to read.
- Select Make searchable, then download the searchable PDF or the plain text.
About this tool
Scanned PDFs are photos of pages, so you can't search them or copy their words. OCR (optical character recognition) reads the words in each page image. This tool keeps your pages exactly as they look and adds an invisible text layer over them, so the PDF can be searched with Ctrl + F, and its text selected and copied.
It reads English, Hindi, Sanskrit, Marathi, Bengali, Gujarati, Punjabi, Urdu, Tamil, Telugu, Kannada and Malayalam, using the free, open-source Tesseract engine. Everything runs on your own device, so a 20-page document takes a minute or two, and longer on phones.
Questions
How accurate is it?
Clean printed pages are usually read very well. Faded scans, small print, handwriting and unusual fonts are harder. Try High quality for small print, and always check important text.
Does the PDF look different afterwards?
No. The original pages are kept as they are. Only an invisible text layer is added, so the file looks the same but becomes searchable.
Why does it download files the first time?
The OCR engine and the language files, a few megabytes, download once from a public library server and are then reused. Your PDF itself is never uploaded.