PDF Modern
🔎

OCR PDF

Convert

Run optical character recognition (OCR) on scanned PDFs to extract text or produce a searchable PDF. Powered by Tesseract WASM in your browser.

📄
Drop a scanned PDF

First run downloads the OCR engine (~12 MB) — subsequent runs are instant.

🔒 100% Private

Files never leave your browser. No upload to any server.

⚡ Instant

Processing runs locally on your device. No queues, no waiting.

🆓 Free & Open Source

No signup, no watermarks, no limits. MIT-licensed code.

Frequently asked questions

How accurate is the OCR?

OCR uses Tesseract WASM, a leading open-source engine. Quality depends on scan resolution — 300 DPI clean scans give the best results.

Which languages are supported?

English by default. More languages can be added on request.

Is it really free and private?

Yes. The OCR engine downloads to your browser once and runs locally. Your PDF never leaves your device.