PDF or text to clean Markdown
Convert a PDF — or pasted text and HTML — into clean, structured Markdown, ready for a RAG pipeline, ChatGPT, Claude or publishing. Headings, lists and paragraphs are recovered from the layout rather than flattened away, which is the part a retriever needs to cite a document properly. The file is opened and processed on your own device and never leaves it — you can watch the Network tab and see nothing uploaded. Headings are inferred from text size, so a PDF that fakes its headings with bold body text will come out flat.
Frequently asked questions
Why convert a PDF to Markdown?
Markdown keeps the heading structure that a plain text dump throws away, and that structure is what a RAG pipeline chunks on and what lets a model cite the right section. It is also the format ChatGPT and Claude read most reliably.
Is my PDF uploaded?
No. The conversion runs entirely in your browser; the file never leaves your device.
Can I convert pasted text or HTML too?
Yes. Leave the drop zone empty and paste into the box instead — HTML is detected automatically and its tags become Markdown, and plain text has its lists and headings inferred.
How does it know what is a heading?
It compares each line against the median text size of that same document, so a 9pt contract and a 14pt slide deck both work. A PDF that fakes its headings with bold body text has nothing to detect, and comes out flat.