Make your scans searchable
A scanned PDF is just an image: you can't search for a word or copy a paragraph. OCR (optical character recognition) reads the image and adds an invisible text layer on top, so the document looks the same but becomes searchable.
Recognition runs with Tesseract inside your browser. The first time, the dictionary for the chosen language is downloaded; your document is never sent to a server. It works in English, Spanish, Portuguese, French, German and Italian.
How to OCR a PDF, step by step
- 1
Select the scanned PDF.
- 2
Choose the document's language and whether you want a searchable PDF or just the text.
- 3
Wait while each page is recognized and download the result.
Frequently asked questions
How long does OCR take?
A few seconds per page on a typical computer. The first run takes a little longer because the language dictionary is downloaded.
How accurate is it?
Results are usually very good on clean scans. Blurry photos, tiny print or handwriting can cause errors: use high quality and review the text.
Is my document uploaded anywhere?
No. Only the recognition engine and the language dictionary are downloaded; the document is processed on your device.