Adaptive AI Educator
Building the podcast format for a multi-format learning platform
A learning platform that teaches aquatic invasive species through several formats at once, published at HCII 2026. I am building the podcast side of the implementation: scripted episodes voiced with ElevenLabs, presenters modeled in Blender, and the whole thing rendered in the browser through Three.js. The research is peer-reviewed and the build is underway.
Results
01The platform
Aquatic invasive species education has to reach people who learn in different ways, and a single lecture format loses most of them. The platform answers that by teaching the same material through several formats, so a learner can pick the one that works for them.
The research behind it is published. What is happening now is the implementation, turning the design in the paper into something people can actually open.
02What I am building
I own the podcast format. Episode audio and presenter voices are generated with ElevenLabs, which keeps a consistent voice across episodes and makes a script revision cheap to re-voice.
Presenter models are built in Blender and rendered in the browser with Three.js, so an episode plays as a scene rather than as a static audio player. Delivering it on the web means a learner needs a link and nothing else.
03Status
Active development. The audio pipeline and the model work are in place and the browser rendering is being built out.