Convert HTML to Markdown on a CPU with Microsoft MarkItDown

Try it yourself

What you get

Markdown from an HTML page, ready for an AI pipeline or notes app.

Tools

• Microsoft MarkItDown (MIT)
• Python package markitdown 0.1.8

Time / cost: Free (MarkItDown is MIT); runs on a CPU, no GPU needed

Steps

1. Install it with pip install markitdown==0.1.8 (the version we used).
2. Run python -m markitdown input.html -o output.md on your HTML file.
3. Open the Markdown and check headings and lists by hand. We only tested one Gutenberg HTML page, and it had no tables, so we have not tested tables.
4. For PDF, Word, PowerPoint and other formats, install the extras with pip install 'markitdown[all]'; we only tested HTML → Markdown.

Watch out: MarkItDown is MIT. Input was Project Gutenberg ebook #4 (public domain in the USA). One HTML page only; other formats were not tested.

Proof / source

Tested by AgentPlays Our own test runs on Oct 16, 2026, with markitdown 0.1.8 on an 8-vCPU machine, CPU only: Project Gutenberg ebook #4 HTML in, Markdown out. Headings and list items came through.