DOCX CVs
Word templates put a lot of the CV outside the main body: the name and contact details in a header or text box, skills in a table, a sidebar in a floating shape. VerbatimCV reads all of it, so those details aren't silently missing from the result.
What simple readers miss
- Text boxes and shapes: common in designed templates; a paragraph-by-paragraph reader skips them.
- Headers and footers: often where the name, email and phone number live.
- Layout tables: two-column templates built as tables; cells are read row by row and assigned to sections by content.
Also handled
- The format is detected from the file's content, not its extension.
- Password-protected files return
ENCRYPTED_DOCUMENTand corrupt onesUNREADABLE_DOCUMENT, rather than an empty result. - Legacy
.docfiles aren't supported; save them as DOCX or PDF first.
Try it
Get a free API key (50 parses a month, no card), then:
curl https://api.verbatimcv.com/v1/parse \
-H "Authorization: Bearer $VERBATIMCV_API_KEY" \
-F file=@cv.pdf
Agents can use the parse_resume tool instead: uvx verbatimcv-mcp. See the
quickstart for Python, JavaScript and MCP setup.