Introducing Empathic Voice Interface 2 (EVI 2), our new voice-to-voice foundation model. EVI 2 merges language and voice into a single model trained specifically for emotional intelligence. You can try it and start building today.

EVI 2 can converse rapidly with users with sub-second response times, understand a user’s tone of voice, generate any tone of voice, and even respond to some more niche requests like changing its speaking rate or rapping. Talk to it here:

It can emulate a wide range of personalities, accents, and speaking styles and possesses emergent multilingual capabilities.

EVI 2 is adjustable. We’ve been experimenting with ways to create synthetic voices unique to any app or user, without voice cloning. Find out more here:

Today, EVI 2 is available in beta for anyone to use. It’s available to talk to via our app and to build into applications via our beta EVI 2 API (in keeping our guidelines).

something about the voice is really off - uncanny valley territory - i think it’s partially the exaggerated enthusiasm

When multilingual capabilities will be presented at least? And when will it be available for developers? I’m interested in real time speech translation.

The model can already outputs several languages (e.g., Spanish, German, French) but currently only understands English inputs. We'll be accepting other language inputs soon, along with more languages!

love it !!!!! Ito for the win

So its not native speech to speech model.

Loved the demo!