You can now control a computer with just your voice. Here’s how we did it: 🧵

We built on @Replit's template to combine Hume’s empathic voice interface with @AnthropicAI's computer use API. EVI processes speech in real time, sends instructions to the agentic computer control loop, explains its actions with voice, and can even be interrupted to change course.

This works because Hume’s frontier speech-LLM, EVI 2, can generate its own language, but can also read out lines from other language models like an actor reading a script. EVI is the only voice-to-voice model that’s both interoperable with any LLM and available today as an API. Learn more here:

👀👉

Try it out with our open-source demo:

Billions in research and she comes up with b4??

wow

hume continues to cook

Finally my computer can get a sense of how frustrating python environemnt management really is :)

in case u missed @kimmonismus @apples_jimmy @sama @OpenAI @GoogleDeepMind @IterIntellectus

this is incredible!