Turn scanned PDFs and images into readable text.
What it does
Extracts Chinese and English text from scanned PDFs and images using local or cloud OCR engines.
When to use it
Use for scanned documents, PDFs with non-copyable text, screenshots, and handwritten or printed text in images.
How to use it
Give it a scanned PDF or image; it extracts and returns the recognized text using the requested or default engine.
What you provide
- Your files
Uses
SI
RA
Good to know
- cannot be undone: SiliconFlow
- acts without asking
- may misreport its own work
Latest review
What you need · 4
The package declares Python 3.6 or later.
Requires requests, imported before the script can reach its automatic dependency installer; requirements.txt specifies version 2.28.0 or later.
Access · 8
This skill
SiliconFlow
Write
Sends documents to cloud OCR (irreversible)
pymupdf
Execute
Installs pymupdf