PDF to EPUB
Turn a PDF’s text into an EPUB eBook.
Converts the text of a PDF into an EPUB 3 eBook for e-readers and reading apps.
How to use it
- Choose a PDF with selectable text. For scanned PDFs, run OCR PDF first.
- Choose how chapters are split, and optionally enter a book title.
- Select Create EPUB and download the
.epubfile.
Options
| Option | Values | Default |
|---|---|---|
| Start a new chapter | One of at detected headings, every 10 pages, every 5 pages, every 20 pages, every page | at detected headings |
| Book title (optional) | Text | None |
Output
An .epub file. The book title comes from the PDF’s properties or the file name, unless you type one.
How chapters are found
With at detected headings, a new chapter starts at lines such as Chapter 3, Part Two: The Return, Prologue or Appendix A. Contents pages are ignored. If fewer than two headings are found, superPDF starts a chapter every 10 pages instead and tells you.
What isn’t carried over
Only text is carried over: images, tables, fonts and page layout are not. Paragraphs are rebuilt from the lines on each page, so poems, lists and multi-column pages may join or split in the wrong places. Pages with no text are left out. Converting EPUB back to PDF isn’t available yet.
Scanned pages
Scanned pages, including copier scans whose text layer is weak or garbled, are read with the quick reader first (the AI tools run OCR PDF for you), so you get a result straight away. On computers that can run it, superPDF then offers high-accuracy reading beside the result, and improves those pages in the background: in Chat and Ask multiple PDFs the pages behind your latest question come first and new questions use the improved text; elsewhere, Run again with the improved text redoes the result. 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. See High-accuracy reading.
Limits
No file size or page limit. Everything runs on your device, so very large files are fastest on a computer.
Privacy
Runs in your browser. Your files are processed on your device and never uploaded.