Afeez Yunus

SOUND ON! 🔉

Why read when you can listen? Experimenting with AI audio interaction, using ElevenLabs' text to speech API, Rive and SwiftUI. We are able to create the contextual visual reactions to what is being said by listening for breaks in the speech (commas, fullstops, viseme time-slots past a certain threshold etc...).

Some expressive Mascot character and text animation I've been experimenting with.

Early attempts at Speech and Expression sync. Using Eleven labs API for text to speech—at least for testing— we generate viseme timestamps that we can then pass to code and then map in Rive.

I plan to add other means of bodily expressions, and obviously the UI, but for a first draft, looks promising.

A growing collection of sports characters