How it works

cappv1 reads a PowerPoint deck or Word document, asks an AI model to describe each picture, chart and table, and writes the answer into that item's alt text. Nothing else in the file changes.

What happens when you run it

  1. You add a deck. cappv1 keeps a copy in its own folder. Your original stays where it is.
  2. It reads each slide. For every picture, table, chart, diagram and embedded object it gathers the item itself, plus the slide's title, section, text and speaker notes as context.
  3. The AI model writes a description. That is the one step that can send content to a cloud service, and only if you chose one. See what is sent.
  4. cappv1 saves a finished copy. The description goes into the item's alt text field. You download the copy from Files.

What it changes, and what it doesn't

The only thing cappv1 ever writes is a shape's alt text, the same field PowerPoint's own Edit Alt Text panel changes. Layout, positions, formatting, pictures, text, notes and slide order are left exactly as they were. It also marks invisible, empty shapes as decorative, which is a pure label and changes nothing you can see.

If someone already wrote alt text

Stopping, resuming and repeating

Always review the results

AI descriptions are good starting points, not guarantees. They can miss context or get details wrong. Open the finished deck, check the alt text in PowerPoint, and edit anything that is off, particularly for charts with exact numbers and for public or legally required material.

Terminal or browser

cappv1 can be used from the terminal (type cappv1) or from this web page (/web in the terminal, or cappv1 --web). Both do the same work, share the same settings, and see the same run.