Editing AI voicing

I was very excited to see the new AI features when I updated Articulate this morning as I returned from a break. Experimenting with the AI text-to-speach for a current project.

Now I'm wondering, is there a way to edit how the speech is generated? Similar type of thing as we can do with SSML formatting, like specifying pronunciation of an acronym, adding a pause or slowing the speech? And more, like one would write an image promt to add some specific characteristics like adjusting intonation or specifying the voice should be friendly or angry?

This works to an extent using the sound effects feature for short phrases, but then the voice is different from one used for other AI voicing, and could vary every time.

This possible? Or on the cards? Would others find it useful?

Looking forward to hearing more about how others are experiencing the new features.