This is neat and straight-forward! Thanks for making it and making games more accessible :)
Viewing post in Caption Tool for Ren'Py comments
To confirm, you mean adding sound captions and not an image caption, correct? While it's not built in to Caption Tool, you can use sound captions in a button action with regular Ren'Py by using the function as an action in your button instead of using activate_sound.
Example:
imagebutton idle "images/mag.png" action [Show("map_mag"), SetVariable("chaptermap", "mag"), Function(play_sound, magazine)] focus_mask True