OCR PDF
Recognise text in scanned PDFs and images with Tesseract OCR. The result is a searchable PDF with an invisible text layer — the original scan stays intact.
Drop your file here
or click to browse
Select fileAccepted: PDF, JPG, JPEG, PNG · Max 25 MB per file
Add at least 1 files to continue.
0 of 10 operations used today
Sign up for free to get higher limits and keep a history of your files. Sign up
Your files stay private
Your file is transferred over an encrypted connection, processed in an isolated environment and permanently deleted after 120 minutes. Files are never shared or used for anything else.
Read our privacy policyHow it works
- 1
Upload a scan
Add a scanned PDF or an image (JPG, PNG).
- 2
Choose languages
Select the languages present in the document for the best accuracy.
- 3
Download
Get a searchable PDF, and optionally the extracted text.
Frequently asked questions
Which languages are supported?
English, French, Arabic, German, Spanish, Italian, Portuguese, Dutch, Turkish and Russian, depending on the language packs installed on the server.
Does OCR change how the document looks?
No. The original images are kept and an invisible text layer is added on top.
How accurate is it?
Accuracy depends on scan quality. 300 DPI scans with clear text give excellent results; enable deskew for crooked scans.