Extract text from images and PDFs (OCR)
Tesseract compiled to WebAssembly, running on your machine. Drop photos or a scanned PDF and get the text out — or a searchable PDF that looks identical to the original.
- Runs entirely in your browser
- Works offline
- No upload
- No sign-up
- No watermark
Loading the tool…
How it works
- Drop images or a PDF.
- Tick the languages present in the document — fewer is faster and more accurate.
- Run the OCR, then copy the text or download a searchable PDF.
Why nothing is uploaded
Every operation on this page is done by code running inside your browser tab, using the same engine that renders web pages. The file is read from disk into your tab’s memory, transformed there, and written back out as a download. It is never sent anywhere — not to us, not to a third party.
Verify it yourself
- Open your browser’s developer tools (F12) and select the Network tab.
- Load your file and run the tool.
- The only requests you will see are the tool’s own code and, once cached, none at all.
Frequently asked questions
Does it handle vertical Japanese?
Yes, with the jpn_vert model. Select it on its own rather than alongside the horizontal one: running both confuses the layout analysis and you get lines interleaved.
What is a searchable PDF?
The original page image with an invisible text layer positioned behind it. The document looks exactly as before, but you can search it, select text and copy from it. It is the standard output of a document scanner, produced here without a scanner.
How accurate is it?
On clean printed text at 300 DPI, very good. On a phone photo with a shadow across the page, mediocre. On handwriting, poor — Tesseract was not designed for it, and no amount of settings will fix that. Resolution and even lighting matter more than any option here.
Where does the language data come from?
From the Tesseract project’s public data CDN, a few megabytes per language, cached after the first use. The images themselves are never sent anywhere: this is the tool where that matters most, because scanned documents are usually the confidential ones.