n8n has no built-in Microsoft Word node, and its Extract From File node, which reads PDF, CSV, HTML, spreadsheets and text files, has no operation for .docx. To get the text out of a Word document, turn it into Markdown for an AI model, fill a Word template or read tracked changes, you install a community node. This guide compares the Word and DOCX packages on our hub, using the description and README each author publishes on npm and our own download data.
What do you need?
| You want to | Look at |
|---|---|
| Convert a .docx to Markdown, for example for an AI model | n8n-nodes-docx-to-md, or n8n-nodes-docx-extractor |
| Get plain text out of .docx or old .doc files | n8n-nodes-word-extractor, or n8n-nodes-docx-converter |
| Fill a Word template with data | n8n-nodes-fill-docx |
| Read, accept or reject tracked changes and comments | n8n-nodes-docx-track-changes |
| Convert Word to PDF | A PDF service node, see PDF in n8n |
Word and DOCX community nodes
Our Word and DOCX hub lists 15 packages that pass our quality rule, with 2,461 npm downloads a week between them. The most downloaded, with the description each author gives on npm (weekly npm downloads as of 28 October 2026):
| Package | Weekly downloads | Latest version | Author’s description |
|---|---|---|---|
| n8n-nodes-docx-to-md | 1,897 | 0.2.2 (20 May 2026) | Convert Docx files to Markdown |
| n8n-nodes-docx-converter | 415 | 0.1.3 (12 October 2024) | Convert Docx to Text |
| n8n-nodes-docx-extractor | 53 | 0.1.0 (31 July 2025) | Docx converter node |
| n8n-nodes-docx-track-changes | 35 | 0.2.1 (1 January 2026) | Extract revisions (track changes) and comments from Word documents |
| n8n-nodes-fill-docx | 14 | 0.2.2 (28 May 2025) | Fill in a DocX template with data from a JSON object |
| n8n-nodes-word-extractor | 12 | 1.0.3 (23 March 2026) | Extract text from .doc and .docx Word files |
Versions and dates come from the npm registry.
n8n-nodes-docx-to-md
The most installed Word package. Its one operation, Convert, turns a .docx from a binary field into GitHub-flavored Markdown, with tables and their headers, headings, lists and basic formatting, and runs Markdown linting on the result. You set the Input Binary Field (default data) and the Destination Output Field (default text), and can turn on Remove Images. Its README lists n8n 1.0.0 or newer.
n8n-nodes-docx-extractor
Converts a .docx from binary input to HTML, text, Markdown or all three, using the mammoth and turndown libraries.
n8n-nodes-docx-converter
Converts a .docx to plain text with the mammoth library. Its README says you give it the path to the file and it outputs the path to the text file it creates, rather than working on binary data. Its last release dates from October 2024.
n8n-nodes-word-extractor
Extracts plain text from both legacy .doc (Word 97-2003) and .docx files, optionally with headers, footers and footnotes. Its README says it is pure JavaScript with no system dependencies; you point Binary Property at the file.
n8n-nodes-fill-docx
Fills placeholders in a .docx template with data, built on the easy-template-x library, and per its README supports complex objects and images. Placeholders use double braces, {{ }}, instead of the library’s default single braces. It is a fork of an older report node with PDF generation removed.
n8n-nodes-docx-track-changes
For document review: extracts tracked insertions and deletions with author and timestamp, extracts comments with replies and resolution status, accepts or rejects revisions by ID or all at once, and returns statistics per author. It can also be used as a tool by n8n’s AI Agent.
Check each node page here for the latest release and, where it has one, its GitHub repository for open issues before you build on a package.
Word to PDF
None of the packages above writes PDF. Among the PDF nodes, n8n-nodes-pdfco lists Document to PDF for RTF, DOC, DOCX and TXT, and n8n-nodes-stirling-pdf converts files to PDF through LibreOffice on your own Stirling PDF server; both are covered in PDF in n8n.
How to choose
- Word documents into an AI or RAG workflow: n8n-nodes-docx-to-md, the most used package, with Markdown tables.
- Plain text, including old .doc files: n8n-nodes-word-extractor.
- Contracts, letters or reports from a template: n8n-nodes-fill-docx.
- Review workflows on tracked changes: n8n-nodes-docx-track-changes.
- Documents in Google Docs instead of Word files: n8n’s built-in Google Docs node.
To install a package on a self-hosted instance, an owner or admin enters its npm name in Settings > Community Nodes; full steps are in How to Install n8n Community Nodes. On n8n Cloud only verified community nodes can be installed, see Verified vs Unverified n8n Community Nodes.
FAQ
Can n8n read a Word document without a community node?
Not directly: n8n’s Extract From File node has no DOCX operation. Use a community node such as n8n-nodes-docx-to-md or n8n-nodes-word-extractor.
How do I convert DOCX to Markdown in n8n?
Install n8n-nodes-docx-to-md and point its Input Binary Field at the file; the Markdown lands in the output field you choose (text by default).
Can n8n fill a Word template?
Yes, with n8n-nodes-fill-docx, which replaces {{ }} placeholders in a .docx with data from a JSON object.
What is the most used Word community node?
n8n-nodes-docx-to-md, with 1,897 weekly npm downloads on 28 October 2026.
