Extract text
~1 credits / page (up to 50)Reads the embedded text layer of a PDF and returns it per page and as a combined string, inline as structured data. Works on any PDF that has selectable text; it does not OCR scanned or image-only documents. Optionally limit extraction to specific pages to reduce cost and noise.
Use when
You want to read, summarize, or quote from a text-based PDF.
Not for
Scanned or photographed PDFs with no text layer (those need OCR).
Cost
~1 credits / page (up to 50)
Billed at 0.1 credits per page read.
Estimated; the actual charge depends on your input and is shown in the response.
What it accepts
Set these inside the intent when you run it.
URL of the PDF to read.
Optional 1-indexed page selector to read only part of the document, e.g. "1-3,5".
What you get back
Extracted text as structured JSON, with per-page text and a combined full-document string.
Run it
Run this sub-skill directly: pin it with operation and pass its inputs in the intent. (Omit operation and the PDF skill will route from your intent instead.)
curl -X POST "https://skill.askfaro.com/skills/pdf/run" \
-H "Authorization: Bearer $FARO_TOKEN" \
-H "Content-Type: application/json" \
-d '{"intent":{"operation":"extract_text","source_pdf":"https://example.com/report.pdf","pages":"1-5"}}'Example requests
- ›Extract all the text from this PDF
- ›Pull the text out of pages 2 through 5 of this report
- ›What does this PDF say?