Portuguese OCR, free and in your browser
Reads Portuguese text (with accents) from photos, screenshots and scanned PDFs, with no account.
● Processed on this device
Loading the tool…
Other tools
How it works
Optical character recognition (OCR) reads the letters in an image. This page uses Tesseract, an open-source engine compiled to WebAssembly and loaded only when you need it. It works on photos of documents, screenshots, posters and scanned PDFs, in Portuguese, English or both.
- Drop the image or PDF.
- Choose “Portuguese”.
- Copy the text.
Limits, stated plainly
The sharper and straighter the image, the better. Small text, handwriting and coloured backgrounds lower accuracy.
Frequently asked questions
Which engine is this?
Tesseract 5 (Apache-2.0), with the “fast” Portuguese and English models, through tesseract.js.