Discussions

Hello, the online demo where user can speak with an AI ‘Wayne’ in real-time is amazing!

What are the limitations on using a custom LLM and voice model? I love the low latency and vocal nuance of Hume AI - can I integrate Hume and HeyGen with custom code?

I would love to create a demo similar to the Wayne demo with a fine tuned avatar and a fine tuned + pre-prompted LLM.

My project is a prototype for an interactive soft skills role play trainer.

Ideally, we would use a customized, fine tuned HeyGen avatar as a realtime, interactive puppet that provides the visual layer, while having some flexibility (and security) around the LLM.

Thanks!