Make a scanned PDF searchable
Make scanned PDFs searchable by adding an invisible text layer.
or drop PDFs and images here
How to use OCR PDF
Scanned documents are only pictures of text, so you cannot search, select or copy from them. OCR reads the words on each page and adds them as an invisible layer exactly where they appear. The page looks the same, but you can now search it, copy from it and have it indexed.
Open a scanned PDF or a set of photos.
Choose the languages used in the document and which pages to process.
Start recognition and download the searchable PDF.
Private by design
Your files are opened and processed inside this browser tab. They are never uploaded to a server.
Questions
Does OCR change how my pages look?
No. The original page image is kept untouched. The recognised text is added as an invisible layer aligned with the words on the page.
Which languages are supported?
English, French, Arabic, Spanish, Italian, German, Portuguese, Dutch, Turkish, Russian, Simplified Chinese and Japanese. You can combine several languages in one document.
Is my document uploaded for recognition?
No. The recognition engine runs in your browser. Language models are downloaded from this website the first time you use them, and your document never leaves your device.
How accurate is the result?
Clean, straight scans at 300 DPI usually give very good results. Blurry photos, handwriting and decorative fonts reduce accuracy. The result screen shows the average confidence so you know when to check.
What about pages that already contain text?
They can be skipped automatically, so digital pages keep their original, exact text.