Document to Markdown for LLMs and RAG (no file retention)

One actor, eight input formats: PDF, DOCX, PPTX, XLSX, HTML, EPUB, RST, and LaTeX in; clean Markdown out. Built for RAG ingestion and agent pipelines: the Markdown also rides INLINE in the dataset item (markdown field), so the next step of your pipeline reads it straight from the dataset with no second fetch.

Why this converter

• The whole intake funnel, one listing. Point your pipeline at this actor and feed it whatever your users upload; the format is picked from the file extension. No per-format actor zoo.
• Reading order that survives two-column PDFs. The PDF path runs a layout pass first, then a structured conversion, keeping multi-column pages in true reading order instead of interleaving the columns line by line - the failure mode that silently poisons RAG chunks.
• Inline output. One dataset row per document with the Markdown in it (capped at 1 MB inline; bigger outputs set markdownTruncated: true and the full file is always in the key-value store).
• No file retention. The input is deleted the moment the conversion finishes. The output file is kept for about an hour, then deleted. Your documents are not stored, mined, or used for anything.
• Failed runs never charge. One dataset item per successful conversion; a failure produces no item and no charge.

How do I convert documents to Markdown on Apify?

1. Press Start with the prefilled sample, or paste your own direct file URL (any of the eight formats).
2. Wait for the run to finish; a typical document takes 10 to 20 seconds.
3. Read the markdown field straight from the dataset row, or download the .md file from the run's Storage tab (the OUTPUT record).

Input

{
  "fileUrl": "https://example.com/report.docx"
}

• fileUrl (required): direct http(s) URL of the document, up to 50 MB. The format comes from the extension (.pdf, .docx, .pptx, .xlsx, .html, .epub, .rst, .tex).
• fileName (optional): set it when the URL has no usable extension; it picks the input format and names the output.
• maxWaitSeconds (optional): how long to wait before failing, default 300.

Output

• One dataset row per successful conversion: pair, fileName, outputFileName, inputBytes, outputBytes, durationSeconds, outputUrl, plus the converted markdown inline (and markdownTruncated).
• The full .md file is stored as the OUTPUT record of the run's key-value store (the dataset row carries its direct outputUrl).

How much does it cost?

$0.15 per successful conversion, platform usage included - the price you see is the whole price. A failed run produces no dataset item and no charge. A free Apify account is enough to use it; conversions bill against your Apify usage balance.

Run it from code

JavaScript (apify-client):

import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: 'YOUR_APIFY_TOKEN' });
const run = await client.actor('hushvert/document-to-markdown').call({
  fileUrl: 'https://example.com/report.docx',
});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items[0].markdown); // the converted Markdown, inline

Python (apify-client):

from apify_client import ApifyClient

client = ApifyClient('YOUR_APIFY_TOKEN')
run = client.actor('hushvert/document-to-markdown').call(
    run_input={'fileUrl': 'https://example.com/report.docx'})
items = client.dataset(run['defaultDatasetId']).list_items().items
print(items[0]['markdown'])

Plain HTTP (one call, returns the dataset row with the Markdown inline):

curl -X POST \
  'https://api.apify.com/v2/acts/hushvert~document-to-markdown/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN' \
  -H 'content-type: application/json' \
  -d '{"fileUrl": "https://example.com/report.docx"}'

Can I use it from n8n, Make, Zapier, or LangChain?

Yes. Like any Apify actor, it plugs into n8n, Make, Zapier, and LangChain through Apify's official integrations; select the actor by name, hushvert/document-to-markdown. AI agents can also call it as a tool through Apify's MCP server, which makes it a natural document-intake step for agent pipelines: file URL in, Markdown out, straight from the dataset.

Is it private?

• The conversion runs on hushvert's server lane, not inside this actor. PDF rides a layout pass + structured pandoc chain; DOCX/HTML/EPUB/RST/LaTeX ride pandoc; PPTX/XLSX ride markitdown. Retention: inputs deleted at conversion end, outputs auto-deleted after about an hour.
• Your documents are never stored beyond that window, never mined, and never used to train anything.

FAQ

Does it OCR scanned PDFs?

No, and it says so instead of guessing: scanned or image-only PDFs fail loudly with no_ocr and are never charged. There is no OCR step.

Which format should I send when the URL has no extension?

Set fileName with the right extension (for example report.pdf); it picks the input format and names the output.

How big can the inline markdown field get?

Up to 1 MB inline. Bigger outputs set markdownTruncated: true and the full file is always in the key-value store at outputUrl.

What is the file size limit?

50 MB per file.

What happens when a conversion fails?

The run fails with the converter's real error message, produces no dataset item, and charges nothing.

More private converters from hushvert

• PDF to Markdown: the dedicated PDF lane with the same reading-order guarantee.
• PDF to DOCX: PDF back to editable Word, real text and tables, correct Hebrew/Arabic reading order.
• DOCX to PDF: Word to PDF.
• Office to PDF: Word, Excel, PowerPoint, OpenDocument, RTF, HTML in; PDF out.
• HTML to PDF: real Chromium render, paste HTML inline for invoices and reports.
• Video to MP4: MOV, MKV, WEBM, AVI, GIF to universal MP4, files up to 500 MB.

Who is behind this actor?

Built by the hushvert founder. The browser-side conversion engine is MIT open source (@hushvert/engine on npm); formats a browser can convert (images, HEIC, audio, archives, PDF page ops) are free and client-side at https://hushvert.com and are deliberately not sold here. Developer API docs: https://hushvert.com/for-developers