Text tool · Free
OCR — Image to Text
Extract text from images and scanned PDFs — in batch, in your browser.
Drop images or PDFs here or click to choose
JPG, PNG, BMP, WebP, TIFF and scanned PDF
What is OCR (text recognition)?
OCR (Optical Character Recognition) is the technology that “reads” the text from an image or scanned PDF and turns it into editable text you can copy, search and paste. Instead of retyping a document, OCR does it in seconds.
What is OCR used for?
- Copy the text from a photo, screenshot or scanned document.
- Digitize paper receipts, notes and contracts.
- Pull excerpts from books, slides and PDFs that won’t let you select text.
- Make a scanned PDF searchable.
How to extract text from an image or PDF
Recognition runs in your browser — files are never sent to a server.
- Choose the text language (Portuguese, English or both).
- Drop one or many images or scanned PDFs.
- Click “Extract text” and copy or download the result as .txt.
Accuracy: printed text vs handwriting
OCR works very well with clear printed text (documents, books, invoices). Handwriting, very stylized fonts and blurry or skewed images reduce accuracy. Tip: use well-lit, straight, high-resolution images for the best result.
Privacy: 100% local recognition
Unlike most online OCR services that upload your files to a server, here everything happens on your own device. Ideal for sensitive documents — contracts, IDs, receipts — that should never leave your computer. No signup and no limits.
Frequently asked questions
What is OCR?
It’s the technology that "reads" text from an image or scanned PDF and turns it into editable text.
Are my files sent to a server?
No. Recognition happens in your browser.
Does it recognize handwriting?
With lower accuracy. It works best with clear printed text.
Which formats can I use?
JPG, PNG, BMP, WebP, TIFF images and scanned PDFs. You can process several files at once (in batch).
Which languages does it support?
Portuguese and English — even mixed in the same document, with the "Portuguese + English" mode.
Why is the first extraction a bit slow?
The first time, the engine downloads the language data (a few MB) and stores it in the browser. The next ones are much faster.
Does it work with multi-page PDFs?
Yes. Each page is recognized and the text comes out together, in order.