# Anything to Markdown

Turn almost any document into Markdown: PDF, Word, PowerPoint, Excel, HTML, EPUB, e-mail, notebooks, CSV.

One tool for an agent or a person to throw any document at. It looks at what the file holds, picks the right converter and returns Markdown a language model reads well. "kind" in the result says what the file was found to be.

- Endpoint: `POST https://setget.net/v1/tools/any-to-markdown` with JSON `{"input": {...}}` (add `"wait": 30` to hold the reply until the job finishes)
- MCP: `run_tool` with `slug` = `any-to-markdown`
- Page: https://setget.net/tools/any-to-markdown

## Files in, files out

This is a file tool. Its file inputs take file references, not file contents and not web addresses.

- Get a reference by uploading: `curl -T FILE https://setget.net/drop/` prints a line `ref  <id>/f1`. Or `POST https://setget.net/v1/drops` with `{"files":[{"name","size"}]}`, PUT the bytes to the returned `upload.url` with the listed headers, and use the file's `ref`. Over MCP use the `drop` tool. A file under about 700 KB can also be sent in place as a `data:<type>;base64,<content>` URI.
- Uploads are at most 100 MB per file, are readable by anyone with the link, and expire (one hour by default). Programs are refused.
- The tool runs as a job. The reply is `{"tool", "ms", "result", "files", "job"}`: `result` is JSON, and every result file comes back in `files` as `{"name", "size", "content_type", "kind", "url", "ref"}`. Download it from `url`, or pass `ref` as the input of another file tool.
- A job still running when the wait ends answers 202 with `job`. Follow it with `GET https://setget.net/v1/jobs/<id>?wait=30`, or stream progress from `GET https://setget.net/v1/jobs/<id>/events` (over MCP: the `job` tool). A person can watch it at `job.url`.

## Inputs

- `file` (required, file, a file reference such as `DROP_ID/f1`): The file to convert: PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx), HTML, EPUB, e-mail (.eml), Jupyter notebook (.ipynb), CSV, JSON, Markdown and plain text.

## Example 1: A Word document

Upload first. Each placeholder below stands for the reference of one upload: `DROP_ID/f1` = [sample.docx](https://setget.net/static/samples/sample.docx).

```json
{"input":{"file":"DROP_ID/f1"},"wait":30}
```

## Example 2: A PDF

Upload first. Each placeholder below stands for the reference of one upload: `DROP_ID/f1` = [sample.pdf](https://setget.net/static/samples/sample.pdf).

```json
{"input":{"file":"DROP_ID/f1"},"wait":30}
```

## Example 3: An Excel workbook

Upload first. Each placeholder below stands for the reference of one upload: `DROP_ID/f1` = [sample.xlsx](https://setget.net/static/samples/sample.xlsx).

```json
{"input":{"file":"DROP_ID/f1"},"wait":30}
```

## Example 4: A saved web page

Upload first. Each placeholder below stands for the reference of one upload: `DROP_ID/f1` = [sample.html](https://setget.net/static/samples/sample.html).

```json
{"input":{"file":"DROP_ID/f1"},"wait":30}
```

**Which files does it take?** PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx), HTML, EPUB, e-mail (.eml), Jupyter notebook (.ipynb), CSV, JSON, Markdown and plain text. The kind is worked out from what is in the file, not from its name, so a wrongly named file still works.

**How do I set options such as a page range or one sheet?** This tool uses the usual settings. For options, use the tool for that kind of file; the result names it in "converted_with".

**What happens to CSV, JSON and plain text?** CSV becomes a Markdown table. JSON is put in a code block. Markdown and plain text are passed through unchanged.

**What about scanned PDFs and pictures?** They hold no text to convert. Use the ocr-pdf tool for a scanned PDF.

**Which kinds are not supported?** The old Office formats (.doc, .xls, .ppt), OpenDocument files, Outlook .msg files, Kindle books and password-protected files. Save them in a current format first.

**Where is the Markdown?** In a file named after your upload, ending in .md. The result also holds the Markdown itself in "markdown" when it is up to 200,000 characters; "truncated" is true when only the start fits there.

**Does it fetch anything from the internet?** No. Links and picture addresses found in the file are copied as text. Nothing they point to is opened or downloaded.
