AI Blocks › Make documents, sheets and slides
Scanned PDF text reader
Give it PDFs, Office files or scans. Get text with page positions, read with OCR when needed, all on your computer.
Scanned PDF text reader is a free AI skill for the job "Make documents, sheets and slides". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · MIT licence · Made by K-Dense · Thinking: low
Made by K-Dense. See the original on GitHub; we copied it as it is, with its licence.
What it does
Text out of PDFs, Office files and scanned images, with the position of every line on the page, all processed on your own computer. Nothing goes to a cloud service. A tool called LiteParse reads the file and returns layout-aware text, structured JSON or rough markdown. For scans it runs OCR with a bundled engine, so pages with no real text still come out. Each piece of text carries a bounding box, so you can cite exactly where something was found. It can also save page images so another model can look at charts or handwriting, and it runs on whole folders. You need Python, and LibreOffice for Office formats.
You give it
- PDFs, Office files or images
- Whether pages are scans
- Output type, such as text or JSON
- OCR language (optional)
You get
- Text from every page
- Bounding box positions
- OCR text for scanned pages
- Page images (optional)
Use it when
- You have scanned contracts and need searchable text.
- You want to feed a folder of papers into a search tool and keep page locations.
- Your documents are private and must not leave your machine.
- You need to cite the exact spot on a page.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.
- It works best when your AI can run Python code and save files.