OCR — Scanned PDF & Image to Text

Pull the text out of scanned documents, photos, and image-based PDFs using on-device OCR. Everything runs locally in your browser, so your documents stay private. English language.

100% in your browserfiles never uploadedno sign-up

Your files are processed in your browser and never leave your device.

Loading tool…

How it works

  1. Upload a scanned PDF or images (PNG/JPG).
  2. Click Extract text — the first run downloads the recognition engine (~10 MB).
  3. Each page is read locally on your device.
  4. Copy the text or download it as a .txt file.

Frequently asked questions

Does OCR run in my browser?

Yes — it uses Tesseract (WebAssembly) entirely on your device. Your files are never uploaded.

Which languages are supported?

Currently English. The engine downloads its language model on first use, then caches it.

Why is the first run slow?

The recognition engine and English model (~10 MB) download once on first use. After that it's much faster.