EpubCCConvert a scanned PDF to EPUB
EpubCC reads scanned pages with OCR and then rebuilds them like any PDF: paragraphs joined, running headers and page numbers removed, chapters detected. The report lists every page read with OCR, because OCR can misread letters on poor scans.
Up to 3 whole books a day free. No account needed.
Updated:
Private files. Never used for training. Deleted automatically, or right away when you press Delete now.
Free for short PDFs, included in Pro and Business
OCR takes far more computing than reading a PDF's own text, so the free plan covers scanned PDFs of up to 10 pages, within its 3 free conversions a day. Pro and Business read scanned pages in the whole book. A longer scan on the Free plan gets a 5-page preview without OCR, and the report shows which pages are scanned.
How it works
- Each scanned page is rendered at high resolution and read with OCR.
- The recognised words go through the same layout engine as any PDF: reading order, paragraphs, running headers, page numbers, footnotes and chapters.
- The quality report lists the pages read with OCR so you can check names, numbers and rare words.
Measured, not promised
On ten pages of an 1867 printing of Alice's Adventures in Wonderland, with the scan's own hidden text removed, EpubCC's OCR matched the reference text better than the OCR layer the scan came with (4-word sequences found: 85.5% against 79.6%). Poor, skewed or handwritten scans do worse, so check the pages the report lists.
Limits
- Languages: English, Spanish, French, German, Portuguese, Italian and Dutch.
- Text inside pictures on normal pages is not read, and handwriting is not supported.
- A scan that already has a hidden text layer is read from that layer, with its own errors.
- OCR is slower: a few seconds per page.
Scanned pages are read with OCR: free up to 10 pages, longer PDFs on Pro and Business. The report lists them so you can check names and numbers.
Start free. Upgrade for longer books.
Free
3 books/day
Whole books, no account. Your EPUB in one step.
Business
$29/month
6,000 pages/month
For heavy readers, teams and libraries: the biggest files and the fastest queue.
View BusinessFAQ
Does it work with scanned PDFs?
Yes: pages that are only a scanned image are read with OCR (English, Spanish, French, German, Portuguese, Italian and Dutch) and the report lists them, because OCR can misread letters on poor scans. OCR is free on PDFs of up to 10 pages; longer scans need Pro or Business.
Is it free?
Yes, for most books: up to 3 whole books a day, each up to 300 pages and 50 MB, with no account. Longer books and scanned PDFs over 10 pages are on Pro and Business.
What happens to my file?
Your PDF is deleted as soon as the whole book is converted, or 2 hours after its last conversion. The EPUB is deleted 1 hour after your first download, or 24 hours after it's ready. Files are never published, and never used for benchmarks or training without your explicit permission.