Convert PDF to Word: editable DOCX with real paragraphs and tables, not text boxes. Pure scans are read by OCR. Per page. Uses AGPL code, source: github.com/BiGapi-2026/bigapi-pdf2docx
curl -X POST https://api.bigapi.dev/v1/pdf/to-docx -H 'Authorization: Bearer $KEY' -F 'file=@contract.pdf' -o contract.docxNew keys come with 100 free operations, no signup: curl -X POST https://api.bigapi.dev/v1/keys. Failed calls cost nothing.
| Name | Meaning |
|---|---|
file required | PDF to turn into an editable Word document. If no page in the range has a text layer (a pure scan), the text is read by OCR and returned as paragraphs, with the warning ocr_applied. Mixed documents keep scanned pages as images (warning no_text_layer). Password-protected PDFs return 422 encrypted_pdf, damaged ones 422 pdf_unreadable. |
first | First page to convert (1 is the first page). Default: first page |
last | Last page to convert. Default: last page |
ocr | auto reads pure scans (no text layer on any page, up to 50 pages) with OCR; off returns them as images like before. Allowed: auto, offDefault: "auto" |
lang | OCR languages for scans as Tesseract codes joined with +, e.g. fra+eng. Same languages as ocr. Default: "deu+eng" |
Returns application/vnd.openxmlformats-officedocument.wordprocessingml.document. Response headers carry the cost (X-BigAPI-Cost) and notes about your input (X-BigAPI-Warnings).
Connect BiGapi as an MCP server: https://api.bigapi.dev/mcp (hosted) or npx -y @bigapi/mcp (local). Then ask in plain words; the agent finds pdf_to_docx on its own.