OCR a scanned PDF
Recognise the text in a scan so you can search and copy it, without changing how the page looks.
or drop them here
Up to 100 MB · 10 files at once
Processed on our own servers, never sent to a third-party service. Files are deleted automatically after two hours, and you can delete them sooner from the result screen.
How to ocr a scanned pdf
- Upload a scanned PDF or photo of a document.
- Pick the language of the text.
- Download a searchable PDF, or the plain text.
The page looks unchanged
Recognised text is placed invisibly behind the original image, so the document looks identical but is now searchable.
Over 100 languages
Including non-Latin scripts. Picking the right language noticeably improves accuracy.
Processed on our own servers
Your file is never handed to a third-party API. It is deleted automatically two hours after upload, and you can delete it sooner from the result screen.
No account needed
Upload, do the work, download. We do not put a sign-up wall in front of the thing you came here to do.
Questions
How accurate is the recognition?
On a clean 300 DPI scan, typically well above 95%. Accuracy falls with low resolution, skewed pages, handwriting and unusual fonts.
Does it work on handwriting?
Not reliably. It is built for printed text; handwriting results vary a lot.
How long are my files kept?
Two hours, then they are deleted automatically. There is also a delete button on the result screen if you want them gone immediately.
Do you look at the contents of my documents?
No. Files are processed automatically and are never read by a person or used to train any model.
Is there a watermark on the result?
No. What you download is exactly what the tool produced.