OCR PDF

On-device OCR with Tesseract. Downloads recognised text as a .txt file.

Checking server…

Extract text from a scanned PDF using on-device OCR (Tesseract). The text is downloaded as a .txt file. Everything runs in your browser.

Choose a PDFPDF only

Document language

Tip: large PDFs and the first run take a while — Tesseract downloads the language model once, then caches it. OCR quality depends on scan resolution.

Related tools

Combine multiple PDFs into one file.

Break a PDF into separate files by page ranges.

Shrink PDF file size with one click.