← Back to Tools

PDF OCR

Extract text from scanned PDFs using optical character recognition

Click to select a PDF or drag it here
Works best with scanned documents and image-based PDFs

Features

  • Extracts text from scanned PDFs and image-based PDFs
  • Powered by Tesseract.js — open-source OCR via WebAssembly
  • 9 language options
  • Process all pages or a custom range
  • Per-page results with confidence score
  • Download extracted text as a .txt file
  • Cancel OCR at any time
  • 100% client-side processing
  • No file uploads — complete privacy
Note: OCR works best on clear, high-resolution scans. PDFs that already contain selectable text do not need OCR — copy the text directly or use the PDF to Word converter. The first run for each language downloads approximately 10 MB of language data; the browser caches this for future runs.