Office Docs to Markdown: DOCX, PPTX, XLSX, HTML, EPUB for RAG

Turn Word, PowerPoint, Excel, CSV, HTML, EPUB and Jupyter files into clean Markdown that LLMs, RAG pipelines and AI agents can use. You get headings, lists, bold/italic text, links, tables as Markdown and JSON, slide titles and speaker notes, sheet data, document metadata, and optional RAG chunks.

Paste document URLs and click Start. Download the results as JSON, CSV or Excel, or use them via API, MCP, Make, Zapier or n8n.

Why this one

• One flat price per document. $2 per 1,000 documents, whatever the format.
• Format detected from the file itself. Links without extensions (/download?id=...), wrong content types and signed URLs all work.
• Word: headings (including Title/Subtitle styles), nested lists, tables with proper header rows, links, bold/italic and footnotes. Inline images are reduced to their alt text, so the Markdown isn't bloated with base64. Images without a description and alt text that is just a file path are dropped.
• PowerPoint:
  • one ## Slide title section per slide;
  • bullet hierarchy preserved;
  • tables, and chart data as tables;
  • speaker notes;
  • <!-- slide N --> markers for citations.
• Excel / CSV:
  • every visible sheet becomes a Markdown table;
  • empty rows, columns and sheets are removed;
  • dates come out as ISO;
  • optional JSON rows keyed by the header row (sheetsAsJson).
• Formula cells: where an Excel formula has no saved value, the formula is shown instead of a blank, with a warning.
• HTML: only the main content by default (no nav, header, footer or scripts).
• Robust.
  • Retries with backoff and file-size limits.
  • Clear error codes: HTTP_404, UNSUPPORTED_FORMAT, ENCRYPTED, CORRUPT_FILE, TOO_LARGE, TIMEOUT...
  • One bad file never stops the run, and failed files are not charged.

Supported formats

Format	Extensions
Word	.docx .docm .dotx
PowerPoint	.pptx .pptm .ppsx
Excel	.xlsx .xlsm and legacy .xls
Delimited text	.csv .tsv
Web	.html .htm
E-book	.epub
Jupyter	.ipynb
Text	.json .xml .txt .md

PDFs: use PDF to Markdown (priced per page, with OCR).

Input

Field	Default	Description
documentUrls	–	Direct document links (required). Up to 5,000 per run.
chunkSize / chunkOverlap	0 / 200	RAG chunks in characters (0 = off).
includePlainText	false	Add a plain-text version.
sheetsAsJson	false	Excel/CSV rows as JSON objects in sheets[].rows.
maxRowsPerSheet	5000	Truncate huge sheets (0 = no limit).
includeHiddenSheets	false	Convert hidden Excel sheets too.
includeSpeakerNotes	true	PowerPoint notes under each slide.
slideMarkers	true	<!-- slide N --> comments.
htmlMainContentOnly	true	Strip navigation/boilerplate from HTML.
includeImageAltText	true	Keep meaningful image descriptions.
maxFileSizeMb	50	Larger files are skipped (not charged).

{
  "documentUrls": ["https://calibre-ebook.com/downloads/demos/demo.docx"],
  "chunkSize": 1500
}

Output

One dataset row per document:

{
  "url": "https://calibre-ebook.com/downloads/demos/demo.docx",
  "status": "ok",
  "format": "docx",
  "fileName": "demo.docx",
  "title": "DOCX Demo",
  "author": "Kovid Goyal",
  "wordCount": 1649,
  "tableCount": 5,
  "markdown": "# Demonstration of DOCX support in calibre\n\nThis document demonstrates ...\n\n| ITEM | NEEDED |\n| --- | --- |\n| Books | 1 |",
  "tables": [{ "name": "Table 1", "headers": ["ITEM", "NEEDED"], "rows": [{ "ITEM": "Books", "NEEDED": "1" }] }],
  "chunks": [{ "index": 0, "text": "...", "heading": "Demonstration of DOCX support in calibre", "chars": 1398 }],
  "warnings": []
}

Spreadsheets add sheetCount and sheets (name, row/column counts, headers, and rows with sheetsAsJson). Presentations add slideCount.

Errors and large results:

• Failed documents get "status": "error" with errorCode and error.
• Very large results (over ~8 MB) are saved in full to the key-value store and linked from fullResultUrl.
• A run summary is saved as OUTPUT.

How much does it cost to convert DOCX, PPTX and XLSX to Markdown?

Pay per event, plus a tiny Actor start fee ($0.00005 per GB of memory):

• Document converted: $0.002 per document ($2.00 per 1,000 documents).

Platform usage is included in the price. Failed downloads, unsupported or damaged files and password-protected documents are not charged. If you set a maximum cost per run, the Actor stops when it is reached.

Limitations (honest)

• Text and structure only. Images are not OCR'd or described; only existing alt text is kept. Use the PDF Actor's OCR for scans.
• Word layout: text boxes, headers/footers and tracked changes may be skipped. Complex merged-cell tables are flattened.
• Excel: values come from the last save in Excel. Formulas are not recalculated. Charts and pivot caches are ignored.
• Not supported:
  • legacy binary .doc/.ppt, OpenDocument (.odt/.ods/.odp) and password-protected files;
  • ZIP archives, so link to the individual files.
• Process only documents you have the right to use. Files are processed inside your run and are not stored anywhere else.

FAQ

Can I upload a file instead of a URL? Upload it to an Apify key-value store, Dropbox (use a ?dl=1 link), S3, Google Cloud Storage or similar, and pass the direct link.

How fast is it? Typically 0.05–1 s per document. A 200-page Word report with 80 tables takes about 7 s.

Does it use an LLM? No. It's a deterministic converter built on open-source libraries (mammoth, python-pptx, openpyxl, markitdown). Output is reproducible and there are no per-token costs.

Use it from AI agents (MCP), the API, Make, Zapier and n8n

• AI agents and MCP clients (Claude, ChatGPT, Cursor, VS Code): add https://mcp.apify.com?tools=pinkish_armada/office-to-markdown as an MCP server, and your agent can convert Word, PowerPoint, Excel, HTML and EPUB files to Markdown as a tool call.
• API: run it and get the results in one request:

curl -X POST "https://api.apify.com/v2/acts/pinkish_armada~office-to-markdown/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"documentUrls":["https://calibre-ebook.com/downloads/demos/demo.docx"]}'

• No-code: use the official Apify apps for Make, Zapier and n8n ("Run an Actor"), then send results to Google Sheets, Slack, Airtable or your database. You can also schedule runs in Apify Console and add a webhook or email integration.

Related tools

• Sitemap URL Extractor: list every URL of a site from its sitemaps, with optional 404 checks
• Broken Link Checker: crawl a website and report broken links, 404s and redirects
• PDF to Markdown: turn PDFs (including scans, via OCR) into Markdown, text and tables
• Domain Lookup: bulk RDAP WHOIS, DNS, SPF/DMARC and SSL-expiry checks for domains