Seus PDFs são processados no navegador e não são enviados. Learn more

PDF OCR: extract the text from a scanned PDF

Scanned PDFs are just images: you cannot copy, search or convert them. With OCR (text recognition), the app reads each page and delivers the text in a .txt file. Recognition runs in your browser, using Tesseract.

OCR PDF

Recognize the text of scanned PDFs with Tesseract and download it as .txt.

Recognition runs in the browser and can take a few seconds per page, depending on the size of the PDF.

Drag your file here or click to choose

Accepted formats: .pdf

How to do it, step by step

Select the scanned PDF.
Click Run and follow the progress page by page.
Download the .txt file with the recognized text.

See where to click, with an image of the tool →

When this is useful

Copy passages from a scanned document

Avoid retyping contracts, minutes and letters.

Prepare to convert to Word or Excel

With the text in hand, you edit and reuse the content.

Tips for a good result

Scan at good resolution and without tilt.
Review the text: names, numbers and accents deserve checking.

What this tool does not do

It can take a few seconds per page, depending on the size of the PDF.
Handwriting and difficult photos have lower accuracy; WebFaz OCR has an optional AI mode for that.

Frequently asked questions

Does the file leave my device?: Not in this tool: the recognition is local, in the browser.
Does it deliver a searchable PDF?: This tool delivers the text as .txt.

More PDF tools

Text written by Marcelo Amantino · updated October 18, 2026 · who we are