High-quality PDF to Markdown converter

Turn a PDF into clean Markdown.

Copying text out of a PDF drags page numbers, headers and broken lines along. WandPDF rebuilds the document as Markdown with real headings, lists and tables.

Text-based PDFs
EPUB, AZW3, MD
Latin scripts, Chinese, Japanese
Deleted after download

PDF to Markdown, before and after

Same page. Two very different Markdown files.

A typical converter dumps the page text line by line. WandPDF writes the structure.

Typical converter pages glued together

the-long-crossing.md 47 / 312

CHAPTER 3 · THE SEA

The tide came in faster than any of them ex-

THE LONG CROSSING

pected, and by noon the

causeway was gone.

³ See the harbour log, 1911.

Nobody spoke on the walk

Page numberRunning headerSplit wordStray footnote

WandPDF text rebuilt

the-long-crossing.md

# 3. The Sea

The tide came in faster than any of them expected, and by noon the causeway was gone.[^3]

Nobody spoke on the walk back.

[^3]: See the harbour log, 1911.

Formats

Convert PDF to EPUB, Kindle or Markdown.

.epub

PDF to EPUB

An EPUB ebook for Apple Books, Kobo, Google Play Books and any reader app. Chapters become a table of contents you can tap.

.azw3

PDF to Kindle (AZW3)

An AZW3 file for Kindle devices and apps. Change the font size and the text flows, instead of zooming a tiny page.

.md

PDF to Markdown

Clean text with headings, lists and tables for notes, Obsidian, a wiki or as input for ChatGPT, Claude and other LLMs.

NextWord is next: an editable document, not a copy of the page layout.

How it works

How to convert a PDF to Markdown

1
Drop your PDF
Any PDF with a text layer: a paper, a report, a manual or a book.
2
Pick Markdown
Headings, lists, tables and footnotes in plain Markdown.
3
Use the .md file
Open it in Obsidian, commit it to a docs repo or paste it into an AI chat.

Under the hood

What a PDF hides, and WandPDF fixes.

01
Page numbers and running headers
Stop showing up in the middle of sentences.
02
Sentences cut by a page break
Are joined back into one paragraph.
03
Hyphenated words
Split at the end of a line become whole words again.
04
Two-column pages
Are read column by column, not straight across.
05
Footnotes
Stay linked to the place they belong to.
06
Pictures and tables
Keep their captions, and text beside a picture stays text.

Tested on 31 books the parser was never tuned on.

Clean means no broken paragraphs, stray page numbers or lost text.

WandPDF23 / 31 clean

The engine most online converters run on2 / 31 clean

FAQ

PDF to Markdown FAQ

Is the Markdown good for ChatGPT, Claude or a RAG pipeline?

That is one of the main uses. Page numbers, running headers and hyphenation are removed and paragraphs are whole, so a model reads the text in order without noise, and chunks can split on real headings.

How are tables converted?

Tables drawn with ruled lines become Markdown tables. Tables without any lines are harder to detect, and some of them still come out as plain text.

Can I use it in Obsidian or Notion?

Yes. Headings, lists, tables and footnotes are plain Markdown, which Obsidian, Notion import, GitHub and most docs tools read.

Does it work with scanned PDFs?

Not yet. WandPDF reads the text layer of a PDF. A scan is a photo of a page with no text inside, and needs OCR first.

Which languages work?

English and other Latin-script languages, plus Chinese and Japanese. Arabic, Hebrew and other right-to-left scripts are still in progress.

What happens to my file?

It is kept only long enough to convert it and let you download the result, then deleted.

Your next PDF deserves clean Markdown.

EPUB, Kindle and Markdown from one upload.

Convert a PDF