Readable text from scans, with gaps called out.
What it does
Extracts text from images, PDFs, and slides while preserving source locations and separating recognition gaps from verified text.
When to use it
Use for extracting text from screenshots, photos, scanned images, image-containing PDFs, and multilingual documents.
How to use it
Give it images, PDFs, or slides; it saves extracted text and reports unrecognized targets and the scope of manual review.
What you provide
- Your files
Latest review
What you need · 6
The bundled OCR helper runs with Python 3.
Requires Surya's foundation, recognition, and detection predictors; installation instructions are provided if the package is missing.
Access · 2
This skill
surya-ocr
Execute
Installs Surya for OCR
transformers
Execute
Installs a compatible Transformers version