English and Czech
Accurate recognition models for English, and for Czech including diacritics.
A scanned contract or invoice is just an image – you can’t select or search its text. Recognize the text with OCR and the PDF becomes searchable.
Drag and drop a PDF here
or
Select scanned PDFUp to 100 MB · opens instantly
Drag the scanned PDF or photos of the document into the window.
Choose the document language (English and Czech are supported) and the pages. Recognition runs in your browser.
Select, copy, search or redact the text. In the downloaded PDF, it stays as a searchable layer.
Accurate recognition models for English, and for Czech including diacritics.
The downloaded page still looks like the scan, but you can search and copy its text.
Find and redact IBANs, email addresses or any text you search for – even in a scanned document.
Text is recognized right in your browser; page images aren’t sent anywhere for OCR.
With a clean scan or photo of a document in a regular typeface, practically everything is recognized. Handwriting, very small print or blurry photos can’t be recognized, or only with errors – so check the result.
Nowhere. Recognition runs right in your browser. The first time you use it, the recognition data (a few megabytes) is downloaded from our server and stays in your browser for next time.
On a computer, usually a few seconds per page; on a phone, longer. You can stop recognition at any time – pages that are already done are kept.
No. The page still looks like the original scan; the recognized text sits beneath it as an invisible layer.
Yes. With the Edit text tool, click a recognized line and retype it – the original spot is covered with the background color and the new text is inserted.
Only you and anyone you send the link to. The document is edited in your browser and only ever reaches our server encrypted. The copy deletes itself one hour after your last edit. Learn more in our privacy policy.