Extract text from a scanned PDF
A scanned PDF is just a photo of each page. OCR turns that image back into text you can copy, search and edit.
Loading the tool…
Other tools
How it works
If you cannot select or copy the text in a PDF, the PDF is really a picture: it was scanned or photographed. This tool checks each page. If a page has real text it copies it as is (fast and exact). If it is an image it reads it with OCR in Portuguese, English or both. The engine runs in your browser, so the contract, the exam or the letter never leaves your computer or phone.
- Drop the scanned PDF (or a photo) in the box.
- Pick the document language: accented Portuguese reads best with “Portuguese”.
- Wait for the progress bar: each page takes a few seconds on a phone.
- Copy the text or download it as .txt.
Limits, stated plainly
OCR struggles with handwriting, blurry photos and badly skewed pages. Always re-read important numbers (amounts, IBANs, dates) before using them.
Frequently asked questions
Is my file sent to a server?
No. The PDF is read and processed on your device. The first use downloads the OCR engine (about 6 MB for Portuguese) from extrair.pt; after that it is cached and processing makes no network requests.
How many pages can I convert?
The site sets no limit. The real limit is your device memory; on an older phone stick to a few dozen pages.
Does it read Portuguese accents?
Yes, it uses the Tesseract Portuguese model, which recognises accents and cedillas. Choose “Portuguese” or “Portuguese + English” for mixed documents.