Rosetta

Convert PDF to Text

PDF → text · digital text-layer PDFs only · not OCR · not chat-with-PDF

PDF to text for developers: extract text from digital PDFs with an embedded text layer via REST parse API or MCP. No OCR for scanned paper. Wire pdf text extraction into Cursor, Claude, and agent pipelines.

PDF to text here means pulling the embedded text layer into markdown and per-page JSON — not OCR on scans. Try the free pdf to markdown converter for a browser preview, or call POST /api/v2/parse / the pdf_parse MCP tool for full documents (200 free credits/month, then paid).

Extract embedded text, then wire the same parse into REST, MCP, or the free converter. Uploads up to 4.5 MB.

Install MCP serverpdf to markdown

Parse a digital PDF

Same POST /api/v2/parse endpoint as the rest of the product. Returns markdown plus per-page JSON from the embedded text layer.

const formData = new FormData();
formData.append("url", "https://example.com/document.pdf");

const res = await fetch("https://rosettafolio.com/api/v2/parse", {
  method: "POST",
  headers: { "X-API-Key": "YOUR_API_KEY" },
  body: formData,
});

const data = await res.json();
response.json
{
  "success": true,
  "markdown": "## Page 1\n\nDocument text...",
  "contents": [
    { "content": "Document text...", "pageNumber": 1, "type": "text" }
  ],
  "pageCount": 12,
  "docId": "doc_abc123"
}

Parse API

POST /api/v2/parse — pdf to text via markdown and per-page JSON from digital PDFs

Parse API docs →

MCP server

pdf_parse, pdf_extract, pdf_split, pdf_ask for Cursor and Claude agent builders

Install MCP server →

Free converter

Try the same parse path in the browser — one conversion, up to 5 pages

pdf to markdown →

Playground

Test parse on a digital PDF without an API key

Parser playground →

FAQ

Does Rosetta OCR scanned PDFs to text?
No. Rosetta extracts text from digital PDFs that already have an embedded text layer. Scanned image PDFs without a text layer are not supported — there is no OCR.
How do I convert PDF to text via API?
POST to /api/v2/parse with your PDF file or URL and an X-API-Key header. The parse response includes markdown and per-page JSON from the embedded text. See the API docs for Node, Python, and cURL examples.
Can I use this from Cursor or Claude?
Yes. Install the Rosetta MCP server (remote Streamable HTTP or npx -y rosetta-mcp) and use pdf_parse to pull text-layer PDFs into agent pipelines. Not a chat-with-PDF product.
Is there a free way to try PDF text extraction?
Use the free PDF to Markdown converter — one conversion, up to 5 pages, max 4.5 MB upload — or the parser playground. Both use the same digital-PDF parse path as the API.

Full documents after signup — 200 free credits/month, then paid. See pricing and API docs.