Skip to content
superPDF

OCR PDF

Turn scanned pages into searchable PDFs and text.

Runs OCR (optical character recognition) on scanned pages and adds an invisible text layer, so you can search, select and copy their text.

How to use it

  1. Open OCR PDF in superPDF.
  2. Choose a document, or pick one saved in My documents.
  3. Enter the pages to use, or leave the field empty to use every page.
  4. Select Recognize text, check the result, then download it.

Options

OptionValuesDefault
PagesPage numbers or ranges, for example 1, 3-5All pages

Output

A searchable PDF that looks exactly like the original, plus the recognized text as recognized-text.txt.

First use

The first time you run it, your browser downloads the English recognition data (about 5 MB) from superpdf.ai and keeps it. Your document never leaves your device.

High-accuracy reading

When a PDF has scanned pages, tables or math, superPDF can offer high-accuracy reading beside the quick result. It reads each page as a picture with a small AI model made for documents (LightOnOCR-3 by LightOn), so it gets the words, tables and math of scans right far more often than the quick reader. It is offered on computers whose browser can run AI on the device (the latest Chrome, Edge or Safari) with 8 GB of memory or more; phones and tablets keep the quick reader. You see the quick result first, then each page is replaced as it is read, with the time left and a Stop button. Once you have chosen it, superPDF uses it by itself in this browser where it helps. It runs on this device: nothing leaves it, and it works offline once downloaded. Download: 871 MB, once, only when you choose it; delete it any time in On-device AI models. Speed: about 10 to 30 seconds a page on a recent computer (the offer shows the time for your pages); up to 20 pages are read at a time unless you choose more or pick pages. It reads English and other European languages best; check results in other scripts, and like any OCR it can misread faded or handwritten text. Running page headers, footers and page numbers are left out of the text. If anything goes wrong, the quick result stays, with a short note.

In OCR PDF, the searchable layer of the PDF comes from the fast reader, which knows where each word sits; the high-accuracy text replaces the text download, as Markdown (recognized-text.md) with tables and math.

Most accurate reading

In the browser, high-accuracy reading reads 20 pages at a time unless you choose more, at about 10 to 30 seconds a page: 2,000 scanned pages would take most of a day. For a whole archive, the superPDF command-line tool on a Mac reads every page of a file, keeps going overnight, and continues where it stopped if you stop it or close the lid (pages already read are kept). It also offers a larger model, more accurate and several times slower.

Terminal
npm install -g @superpdf/cli
superpdf model download
superpdf export archive.pdf --high-accuracy --output archive.md
superpdf model download --model 4b
superpdf export archive.pdf --high-accuracy --model 4b --output archive.md

Run the same export command again after a stop to continue. Everything runs on your computer; nothing is uploaded. See PDF CLI for sizes and speeds.

Limits

No file size or page limit. Everything runs on your device, so very large files are fastest on a computer.

English text only. Pages that already have searchable text are skipped, so running OCR twice doesn’t duplicate text. Expect a few seconds per page; handwriting and very low-quality scans give poor results.

Privacy

Runs in your browser. Your files are processed on your device and never uploaded.

Open OCR PDF