Tools/document-converter

Document Converter

Active

Your agent can't convert document formats itself; this turns Markdown, DOCX, HTML, PDF, and more into each other.

1 tool

Convert documents between Markdown, GFM, HTML, DOCX, RST, LaTeX, EPUB, plain text, and PDF. 0.5 credits per MB of input.

Documentsconvertdocumentmarkdownpdfdocxhtml

Tools (1)

▶convert

Convert a document between Markdown, DOCX, HTML, PDF, RST, LaTeX, EPUB, and more.

Usage-based · 0.5 credits per MB of input

Example prompts

“Convert this Markdown release notes file to DOCX and give me a download link”
“Take the attached HTML report and produce a PDF version”
“Convert this DOCX meeting minutes into clean Markdown so I can paste it into a wiki”

Parameters

input_urlstringrequired

Pre-signed GET URL of the file to convert. Obtain via POST /uploads/presign on faro-api.

expires_inintegeroptionaldefault: 3600

Seconds the download URL stays valid (default 1h, max 24h).

input_formatstringoptionaldefault: "auto"

Pandoc input format. `auto` infers from filename/extension in input_url.

output_formatstringrequired

Pandoc output format. PDF is rendered via weasyprint (no LaTeX); math/bibliography use cases are out of scope for v1.

output_filenamestringoptional

Filename for the generated output. Defaults to `output.<ext>`.

API Usage

curl -X POST "https://skill.askfaro.com/skills/document-converter/run" \
  -H "Authorization: Bearer faro_<your_key>" \
  -H "Content-Type: application/json" \
  -d '{
  "intent": {
    "prompt": "Convert this Markdown release notes file to DOCX and give me a download link"
  }
}'

CLI Usage

askfaro describe document-converter/convert

Install pip install askfaro-cli, then askfaro auth login.

▶README

Document Converter

Convert documents between common formats. PDF output is rendered via an HTML→PDF engine, math typesetting and bibliography features are out of scope.

Workflow

Call POST /uploads/presign on faro-api to get a put_url + get_url pair.
PUT your input file to put_url.
Call this tool with input_url = get_url and the desired output_format.
Download the result from the returned download_url (default 1h TTL, max 24h).

Supported formats

Input	Output
markdown, gfm, html, docx, rst, latex, txt, epub	markdown, gfm, html, docx, rst, latex, pdf, epub, plain

Use input_format: "auto" to infer from the input filename.

Inputs

Name	Type	Default	Description
`input_url`	string	required	Pre-signed GET URL of the source file.
`input_format`	string	`auto`	Source format. See list above.
`output_format`	string	required	Target format. See list above.
`output_filename`	string	`output.<ext>`	Filename in the download URL.
`expires_in`	integer	`3600`	Download URL TTL in seconds (60 – 86400).

Output

{
  "download_url": "https://…/output/…/output.pdf",
  "key": "output/…",
  "size_bytes": 84221,
  "mime": "application/pdf",
  "input_bytes": 4231,
  "expires_at": "2026-05-15T13:00:00Z"
}

Pricing

0.5 credits per MB of input. A 3.2 MB DOCX costs about 2 credits.

Max input size: 200 MB.

Not supported

Math equations in PDF output, bibliography rendering, .tex → PDF compilation, and other LaTeX-only features. If those matter to you, request output_format: "latex" and compile to PDF yourself.