OCR PDF
Recognise the text in scans and photos and turn a PDF into a searchable document or a plain text file. Choose the language, page range and resolution; Tesseract runs in your browser and your file never leaves the device.
How it works
- 1
Pick the languages
Select every language that appears in the document — mixing them is supported.
- 2
Choose the output
A searchable PDF keeps the page image, plain text gives you a .txt file.
- 3
Run OCR and save
Pages are recognised one by one; a large scan can take a while.
Your privacy is the point
This tool runs entirely in your browser using WebAssembly and Canvas. Your file is never uploaded to a server, never stored and never seen by anyone but you.
Frequently asked questions
Why does the first run take so long?+
Tesseract loads its engine and language data (roughly 10–20 MB per language) from a CDN the first time you use it. Later runs use the browser cache and start much faster.
How accurate is the text?+
Clean, 300 DPI scans of printed text are usually excellent. Handwriting, skewed photos, decorative fonts and low-resolution scans are much worse. OCR never invents text, but it can misread similar characters — proofread anything important.
Related tools
All toolsEverything runs locally. No uploads, no server-side copies.