Documents
Document-to-Markdown Converter
Upload a DOCX or text-based PDF and extract bounded Markdown in a restricted CPU worker.
Processed on our CPU server.Uploaded files use single-use private references, expire after five minutes and are removed on conversion. No external requests or OCR.
2048 KiB limitInput
Result
A useful result starts here.
Paste your input or load an example,
then run the tool.
Supported formats & limitations
- Pinned pypdf 6.19.0 / defusedxml 0.7.1. Worker has no network, one conversion at a time, six CPU seconds, eight-second client budget and bounded memory/output.
- DOCX: 200 archive entries, 4 MiB expansion, 100x ratio, 1 MiB per entry. Common heading styles, flattened lists, simple tables. No macros, external relationships, images, headers/footers or layout fidelity.
- PDF: up to 20 text pages, 2 MiB decoded page stream, 256 KiB Markdown. Reading order/structure may be lost. Encrypted/scanned/empty/corrupt files rejected. No OCR, models or URL ingestion.
- HTTP multipart uploads return single-use capability references for MCP. Unused files expire after five minutes; consumed input is removed before conversion even on failure. Physical cleanup every 30 seconds/startup.
Execution budget: 10s; output limit: 4096 KiB. Browser worker startup has a separate 3s allowance.