OCR

OCR — turn scans into searchable PDFs

Recognize text in scanned PDFs and photos with Tesseract OCR. The result looks identical to your scan, but you can search, select and copy every word — in up to 4 languages at once.

20+ languages, mix up to 4 Auto-rotate & deskew crooked scans Searchable PDF, PDF/A or plain text Accepts PDFs and photos

Try it now — sign in when you're ready to process. New accounts get 10 free credits.

Sign in Create account

Choose files

or drop them here · paste with Ctrl+V

PDF, JPG, PNG, GIF, BMP, TIFF, WEBP, HEIC · up to 25 MB each · max 20 files

Encrypted transfer Deleted after 2h No watermark

How it works

PDF OCR in three steps

01

Upload

Drop scanned PDFs or photos (JPG, PNG, TIFF…). Several images become one PDF.

02

Pick languages

Choose the languages printed on the page, e.g. English + Indonesian.

03

Download

Get a searchable PDF (or .txt) — copy, search and index every word.

Frequently asked

Which languages are supported?

Every Tesseract language pack installed on this server is listed. Mixing languages (e.g. Indonesian + English) improves accuracy on bilingual documents.

My PDF already has some text — what happens?

"Skip pages with text" leaves digital pages untouched and only OCRs scanned ones. "Force" rasterizes everything and OCRs again.

How accurate is it?

Clean 300 DPI scans typically reach 98–99% accuracy. Turn on deskew and auto-rotate for phone photos.