PDF OCR - Convert Scanned PDF to Searchable PDF / Text File
Add scanned PDFs, choose the language of the text, and tap Start OCR. You get a searchable PDF and/or a plain text file. Online App to Recognize Text in Scanned PDF documents
PDF OCR
Drop PDF files here, or choose below
How to use
Add scanned PDFs, choose the language of the text, and tap Start OCR. You get a searchable PDF (the original pages with an invisible text layer on top) and/or a plain text file. Everything runs on your device; only the OCR engine and language data are downloaded the first time.
Tips for better results
Use Best quality for small print, choose the right language, and turn on Enhance scan in Settings for faded or gray scans. Pages that already contain text are skipped by default.
FAQ
Why does it download data? The OCR engine and each language pack are fetched once from a CDN, then cached by your browser.
Which languages? All the languages Tesseract provides, over 100. Pick a main language and add up to 3 more for mixed documents. Each language is a one-time download, from a few MB to about 20 MB for Chinese.
Other alphabets? They are recognized, but the searchable PDF can only embed Latin letters, so use the Text output for those.
Is it slow? A page takes a few seconds, more at Best quality.
Settings
Recognized text
Languages
Tool to search, edit, modify PDF content. Digitize scanned documents, convert PDFs content into editable text,extracting text from PDFs. Recognize text in Pdf files via OCR.