Document to Markdown for AI — PDF, Word, PowerPoint, Excel and web pages

Turn documents into clean Markdown that LLMs understand. Paste links to PDFs, Word files, slide decks, spreadsheets or web pages and get structured Markdown with headings, lists and tables kept. You also get word and token counts, and optional ready-to-embed chunks for RAG.

Works with Google Drive, Google Docs/Slides/Sheets and Dropbox share links.

Supported formats

Format	What is kept
PDF	Headings (detected from font size), paragraphs, bullet and numbered lists, re-joined hyphenated words, optional page markers, title and author
Word (.docx)	Headings, bold/italic, lists, tables, links
PowerPoint (.pptx)	One section per slide with its title and bullets, plus speaker notes
Excel (.xlsx)	One Markdown table per sheet
Web pages	Main article only (menus, ads and footers removed), absolute links
CSV, TXT, Markdown, JSON	Tables, cleaned text, pretty JSON

Scanned PDFs without a text layer are flagged with needsOcr: true and not charged.

Output

{
  "status": "ok",
  "url": "https://arxiv.org/pdf/1706.03762",
  "fileType": "pdf",
  "title": "Attention Is All You Need",
  "markdown": "## Attention Is All You Need\n\nAbstract\n\nThe dominant sequence transduction models...",
  "chunks": ["## Attention Is All You Need\n\n...", "..."],
  "wordCount": 6230,
  "tokensEstimate": 10950,
  "pageCount": 15,
  "needsOcr": false,
  "metadata": { "author": null, "createdAt": "D:20240410211143Z" },
  "warnings": []
}

How to use it

1. Paste one or more document URLs (public links).
2. Optional: set a chunk size (for example 2000 characters) to get chunks for embeddings.
3. Run, then download the results as JSON or CSV, or send them to your vector database, LangChain, LlamaIndex, Make, Zapier or n8n.

AI agents can call this actor through the Apify MCP server to read any document by URL.

Pricing

You pay per document converted, whatever its size (up to the page and size limits you set).

• Failed downloads, unsupported files and scanned PDFs with no text are free.
• Set a maximum cost per run in the run options; the actor stops cleanly at that limit.

Use cases

• RAG and chatbots: load manuals, policies and reports into a knowledge base.
• AI agents: let an assistant read PDFs, decks and spreadsheets from a link.
• Content and research teams: pull clean text out of reports and slide decks.
• Data pipelines: normalise mixed document collections into one text format.

Limits

• Only public links. Files behind a login cannot be downloaded.
• Web pages are fetched without running JavaScript; pages that build their content in the browser may come back thin.
• Old binary formats (.doc, .ppt, .xls) are not supported; save them as .docx, .pptx or .xlsx.
• Text inside images is not read (no OCR yet).

Support

Found a document that converts badly? Open an issue on the Issues tab with the link. We reply within one business day and use these reports to improve the converter.