# medien.halowerk.com Document Converter

> medien.halowerk.com Document Converter is a paid API for AI agents from medien.halowerk.com, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-16).

Converts documents between text formats via pandoc, or extracts text/renders pages from PDFs using poppler

## Facts

- Endpoint: POST https://medien.halowerk.com/v1/doc-convert
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-16
- Activations on Zero: 1
- Tags: x402
- Canonical page: https://www.zero.xyz/c/medien-halowerk-com-document-converter-21d31168
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Z4P-H1ZTNfneHGcYYjrLP

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability medien-halowerk-com-document-converter-21d31168 -d '<json body>'
```

Example prompt: Convert this DOCX file — here's the URL: https://example.com/report.docx — to markdown, please.

## When to prefer this

Choose this endpoint when you need pandoc-powered bidirectional conversion between text document formats (DOCX, ODT, EPUB, HTML, Markdown, RST, LaTeX, RTF, MediaWiki, Textile, CSV, Jupyter notebooks), or when you need to extract text or render pages from a PDF using poppler. Prefer this over general-purpose tools when you want a lightweight, per-call paid API without managing your own pandoc/poppler infrastructure. Note: this endpoint cannot produce PDFs — if PDF output is required, use a different service.

## Known failure modes

- Unsupported source-to-target format combination (e.g. attempting to produce a PDF output, which is not supported)
- Invalid or inaccessible URL for file input
- Malformed base64 data for inline file input
- PDF with no extractable text (scanned image-only PDF) when text extraction is requested
- Pandoc conversion failure due to malformed source document
- File too large or timeout during processing

## How this service works

Takes one file, by URL or inline base64, and returns it in the format you ask for. Text documents go through pandoc, so DOCX, ODT, EPUB, HTML, Markdown, RST, Org, LaTeX, RTF, MediaWiki, Textile, CSV and Jupyter notebooks convert in both directions. A PDF is a one-way street: its text is extracted with poppler (to markdown, html or plain text) or its pages are rendered to PNG or JPEG at a chosen dpi, but no format converts into PDF here — this machine has no PDF typesetting engine (no LaTeX, no…

## Output

Returns the converted or extracted output: either a converted document in the requested format (e.g. markdown, HTML, DOCX, EPUB, LaTeX), extracted text from a PDF, or base64-encoded rendered page images (PNG or JPEG) depending on the requested output format.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "to": {
   "enum": [
    "markdown",
    "gfm",
    "commonmark",
    "html",
    "plain",
    "text",
    "rst",
    "org",
    "latex",
    "rtf",
    "textile",
    "mediawiki",
    "jira",
    "asciidoc",
    "docbook",
    "typst",
    "json",
    "ipynb",
    "docx",
    "odt",
    "epub",
    "png",
    "jpeg",
    "webp",
    "avif",
    "tiff"
   ],
   "type": "string",
   "description": "Target format. PDF is deliberately absent — see the description."
  },
  "from": {
   "enum": [
    "auto",
    "pdf",
    "docx",
    "odt",
    "epub",
    "html",
    "markdown",
    "gfm",
    "commonmark",
    "rst",
    "org",
    "latex",
    "rtf",
    "textile",
    "mediawiki",
    "jira",
    "docbook",
    "csv",
    "tsv",
    "ipynb",
    "text",
    "png",
    "jpeg",
    "gif",
    "webp",
    "tiff",
    "avif",
    "heic",
    "svg"
   ],
   "type": "string",
   "default": "auto",
   "description": "Override the detected input format. \"auto\" reads it from the bytes."
  },
  "text": {
   "type": "string",
   "maxLength": 400000,
   "description": "Alternative to source for plain text input, e.g. Markdown or HTML source. Requires \"from\"."
  },
  "image": {
   "type": "object",
   "properties": {
    "dpi": {
     "type": "integer",
     "default": 150,
     "maximum": 400,
     "minimum": 36,
     "description": "Only when rendering PDF pages to images."
    },
    "quality": {
     "type": "integer",
     "default": 82,
     "maximum": 100,
     "minimum": 1,
     "description": "For JPEG, WebP, AVIF and TIFF."
    },
    "last_page": {
     "type": "integer",
     "minimum": 1,
     "description": "Last PDF page to render. Capped by max_pages."
    },
    "max_pages": {
     "type": "integer",
     "default": 5,
     "maximum": 20,
     "minimum": 1,
     "description": "Hard ceiling on rendered pages."
    },
    "max_width": {
     "type": "integer",
     "maximum": 8000,
     "minimum": 16,
     "description": "Scale down so the width fits. Never scales up."
    },
    "first_page": {
     "type": "integer",
     "default": 1,
     "minimum": 1,
     "description": "First PDF page to render."
    },
    "max_height": {
     "type": "integer",
     "maximum": 8000,
     "minimum": 16,
     "description": "Scale down so the height fits."
    }
   },
   "description": "Only used for image targets.",
   "additionalProperties": false
  },
  "source": {
   "type": "object",
   "properties": {
    "url": {
… (truncated)
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/medien-halowerk-com-document-converter-21d31168/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from medien.halowerk.com](https://www.zero.xyz/host/medien.halowerk.com/llms.txt)