Image OCR

Extract text from an image — supports Portuguese, English and Spanish. Powered by Tesseract.js, 100% in your browser.

How to use

  1. Upload an image (JPG, PNG, WebP or BMP, up to 20 MB).
  2. Select the language(s) present in the image.
  3. Click Extract — the text appears in a text box you can copy or download.

About this tool

This tool uses Tesseract.js — the most widely used open-source OCR engine, compiled to WebAssembly — to recognize text in images. It supports over 100 languages; this interface offers Portuguese, English and Spanish. The recognition runs entirely in your browser.

The first use downloads the OCR engine and trained language data (~4 MB per language) from a CDN. After that, the data is cached by your browser. Recognition accuracy depends on image quality — clean, high-contrast scans produce the best results.

Common uses: extracting text from a screenshot, digitising a printed document or receipt, or copying text from a photo of a whiteboard. The tool works best with printed text; handwriting recognition is limited.

Frequently asked questions

Does my image leave my browser?

The image itself stays local. The OCR engine and language data are downloaded from a CDN (cdn.jsdelivr.net) on first use, but your image is never uploaded.

How accurate is it?

Very accurate for clean printed text (newspapers, books, screenshots). Less accurate for handwriting, low-resolution photos, or text on complex backgrounds.

Can I OCR a PDF?

Not directly. Convert the PDF to images first using the PDF to Image tool, then OCR each page.

Why does the first run take so long?

The Tesseract engine (~4 MB per language) is downloaded once. Subsequent runs are much faster because the data is cached.

Related tools

Long links? Shorten them for free

Vai.la turns any URL into a short link with click statistics, QR Code and your own biolink.

Vai.la is not responsible for how the tools are used or for decisions made based on their results.