Skip to content

PDF to EPUB converter

PDF is rasterized or read page-by-page and AI Deep Read produces EPUB text for pdf-to-epub.

  • Converted with AI Deep Read · input deleted within 24 h
  • Free: 5 conversions a day · 5 MB each
  • Higher limits →

What changes

  • PDF is rasterized or read page-by-page and AI Deep Read produces EPUB text for pdf-to-epub.
  • AI Deep Read uses 1 credit per page and is not available anonymously; sign in and see /pricing for credit packs.
  • The organization-configurable model transcribes visible text, headings, lists, forms, checkboxes, captions, and tables in reading order.
  • OCR does not recover hidden text layers, passwords, redacted content, embedded files, comments, or document metadata.
  • EPUB output favors clean semantic text over exact visual positioning.
  • Illegible regions are marked instead of invented; scans, handwriting, skew, and low contrast affect accuracy.

A real PDF → EPUB run

We converted our PDF sample (91 KB) with AI Deep Read under AI Deep Read on 2026-09-11. It took 4.7 s and produced a 5 KB EPUB file, 94% smaller than the input. The engine raised 1 warning, listed below.

Input · sample.pdf · 91 KB

PDF 1.4, 1 page, no text layer, 1 image object

Version
1.4
Pages
1
Images
1
Text layer
no

Output · sample.epub · 5 KB

EPUB 3.0: 3 content documents, 0 images, EPUB 3 nav, no cover

Version
3.0
Content documents
3
Images
0
Table of contents
EPUB 3 nav
Cover
no cover
  • AI Deep Read read 1 page; 1 credit per page

Options

pageRange
OCR only selected PDF pages before charging page credits.
maxPages
Cap the number of pages processed for cost and speed control.
extractTablesAsGfm
Return detected tables as GitHub-flavored Markdown pipe tables.
preserveLayout
Keep visible columns and sections when they help comprehension.
languageHint
Tell the OCR model which language to expect when auto-detection is not enough.

Example

input
PDF scan or photo page with headings, tables, and form labels
output
EPUB OCR text in reading order; uncertain text marked [illegible]

Do it in code

cli
curl -X POST https://filetypeconverters.com/api/v1/convert \
  -F from=pdf -F to=epub -F file=@input.pdf \
  -o output.epub

PDF to EPUB by API or MCP

The HTTP API and the MCP server run the exact engine this page uses (AI Deep Read); the response carries the same warnings the web converter shows. Check support first with GET /api/v1/pairs?from=pdf&to=epub.

curl
curl -X POST https://filetypeconverters.com/api/v1/convert \
  -H "Authorization: Bearer $FTC_API_KEY" \
  -F "file=@input.pdf" -F "from=pdf" -F "to=epub" \
  -F "deepRead=true" \
  --output output.epub
API reference

Related conversions

This converter works today; a tested write-up of what changes for PDF → EPUB is in progress.