PDF to Markdown

Convert PDFs — local files or ones already open in your browser — into structured Markdown.

Do my local files get uploaded anywhere?

Yes. PDF-to-Markdown is server-side: Web2MD reads the PDF from the browser tab or file picker and sends the file over HTTPS to the Web2MD conversion service. Raw PDF uploads are processed in memory rather than saved as source files. This differs from Markdown-to-PDF export, which creates the PDF locally in your browser.

Web2MD data-processing boundaries · Local Markdown-to-PDF export is a separate, browser-only workflow

How to convert a PDF to Markdown

  1. For a PDF already open in your browser (a spec sheet, a paper, a report): click the Web2MD icon. Web2MD reads the PDF from that browser session and sends the file to its conversion service over HTTPS.
  2. For a PDF on your computer: allow the extension to access file URLs, open the PDF in a browser tab, then convert it the same way. The PDF file is uploaded for server-side extraction.
  3. Copy the Markdown or send it directly to ChatGPT or Claude. Headings, lists, and tables keep their structure instead of collapsing into one run of text.

Why convert PDFs to Markdown?

PDF is a layout format, not a content format — it describes where glyphs sit on a page, not what is a heading and what is a footnote. Copy-pasting a PDF usually produces broken line-wraps mid-sentence, page numbers stranded inside paragraphs, and tables flattened into unreadable columns.

Markdown gives the model the document's actual shape: headings stay headings, lists stay lists, tables stay tables. That is the difference between an AI summarising your report correctly and it mistaking a table header for a sentence.

Long PDFs are also token-expensive. Stripping the repeated headers, footers, and page furniture that appear on every page can cut a document substantially before it reaches the model's context window.

PDF to Markdown — FAQ

Does it work on scanned PDFs?

Only if the PDF has a text layer. Many scanned documents are just images of pages with no selectable text — there is nothing to extract, so those need OCR first. If you can select the text in your PDF reader, Web2MD can convert it.

Are tables preserved?

Simple tables convert to Markdown tables. Complex layouts — merged cells, nested tables, multi-column academic papers — are genuinely hard in PDF and may need a manual tidy-up afterwards.

Do my local files get uploaded anywhere?

Yes. PDF-to-Markdown is server-side: Web2MD reads the PDF from the browser tab or file picker and sends the file over HTTPS to the Web2MD conversion service. Raw PDF uploads are processed in memory rather than saved as source files. This differs from Markdown-to-PDF export, which creates the PDF locally in your browser.

Is it free?

The web converter includes one anonymous conversion per day and three per day on a free account. The extension's dedicated PDF workflow requires Pro.

Converting a web page instead? Use the website to Markdown converter. For video transcripts, try YouTube to Markdown. Site-specific guides live in the convert hub.

Other file formats: Word (.docx) · Excel (.xlsx) · PowerPoint (.pptx) · PDF