PDF to Markdown Converter

Prepare text for an AI chat

Extract text from a text-based report or article before pasting it into an AI chat.

Example: Convert a report, then check the output for reading-order changes before using it in ChatGPT or Claude.

Move a manual into a docs site

Create editable Markdown text for a wiki, documentation site, or knowledge base.

Example: Convert a product manual and review its headings and lists before publishing.

Make notes from a paper

Move text from a lecture handout or paper into Obsidian, Notion, or another Markdown editor.

Example: Extract a text-based paper and edit the Markdown into study notes.

Prepare text for retrieval workflows

Use detected headings as possible boundaries when preparing document text for a RAG workflow.

Example: Review the Markdown and choose chunk boundaries manually before indexing it.

Is my PDF uploaded to a server?

No. The conversion runs in your browser, so your PDF and its text are not uploaded or stored on our servers. The page loads standard analytics that record visits, but they do not receive your file or its contents.

Can I convert a scanned PDF to Markdown?

Not directly. A scanned PDF is made of page images with no text layer, so there is no text to extract. Run the file through the OCR PDF tool first, then convert the searchable result. If image-only pages contain extractable images, the tool still offers them in a ZIP and explains that no text was found. If no text or images can be extracted, it shows an error instead of producing an empty file.

What happens to tables?

Tables are not converted into Markdown tables. Their contents are extracted as text lines, so you may need to rebuild the table by hand.

Are headings, bold, and italics preserved?

Headings are inferred from font size, so clearly larger titles may become Markdown headings (#, ##, ###). Limited bold all-caps headings may also be detected. Bold and italic styling is not retained; bullet and numbered list prefixes are kept.

What happens to images in my PDF?

Some embedded images can be extracted as PNG files and referenced in the Markdown. When images are extracted, the download is a ZIP with the Markdown file and an images folder. If image decoding fails, some images may be skipped; the result reports how many images were extracted and skipped. Images are only in the ZIP; the Copy Markdown button can include or leave out their references.

How do I copy the Markdown without downloading?

Use the Copy Markdown button after conversion. It copies exactly the text shown in the preview. When images were extracted, use the Include image references checkbox to control whether image-reference lines are copied. Image files themselves are only in the ZIP.

Is the output good for ChatGPT, Claude, or RAG pipelines?

It can help prepare text-heavy PDFs such as articles, manuals, and reports. Repeated text in page margins and standalone page numbers are filtered when detected, and headings may provide useful chunk boundaries. Review the result because multi-column layouts and tables may need manual cleanup.

Is there a file size or page limit?

Yes. Each PDF can be up to 50 MB and 300 pages. Large or image-heavy files can take longer because processing runs in your browser. Use Extract Pages or Split PDF to process a shorter document.

Is it free?

Yes. The tool is free to use, requires no sign-up, and does not add a watermark. The per-file size and page limits still apply.

What about password-protected PDFs?

Password-protected PDFs cannot be read by this converter. Remove the password first with the Unlock PDF tool, then convert the unlocked file.