Access EVI 3 Preview in the Hume iOS App

EVI 3, currently in preview, is available to chat with in our iOS app. Speak with any voice and personality you create with a prompt. Create your own empathic AI. 

Image (34)

EVI 3 API coming soon

EVI 3 is a speech-language model that streams in user speech and forms natural, expressive speech and language responses. With deep speech and language understanding, EVI 3 brings more expressiveness, realism, and emotional understanding to voice AI. And instead of being limited to a handful of speakers, EVI 3 can speak with any voice and personality you create with a prompt.

Image (38)

Our model capabilities

Emotional Intelligence

EVI 3 analyzes the tune, rhythm, and timbre of your speech to pick up on emotional cues, outperforming other models–which only process words–in identifying emotions like fear, excitement, joy, and surprise. It can generate authentic emotional expressions on command. Tell it to sound amused and it chuckles; ask it to sound anxious and it stammers.

Context Injection

EVI 3 seamlessly integrates real-time information, injecting context tokens without breaking conversational flow. Ask "What's the current conversion rate for euros to dollars?" and EVI 3 pulls live data as it responds. The model runs advanced search, reasoning, and tool use systems in parallel, enabling it to "think fast and slow" like frontier AI systems without sacrificing latency.

Custom Voices

EVI 3 can adopt any of the 100,000+ custom voices and personalities created on Hume's text-to-speech platform. Simply describe the voice you want - "sound like a wise professor" or "speak with a cheerful morning radio host tone" - and EVI 3 adapts its speaking style, from vocal timbre to personality traits. EVI 3 is the first truly personalized voice AI experience, surpassing traditional preset options.

Frequently asked questions

Trusted By

Design Works Logo
Lge Logo
Woven Logo
Softbank Logo
Humana Logo
Aecho AI Logo
Betteryou Logo
Nestwork Logo
Innovax Systems Logo
Jammy Chat Logo
Aura Health Logo
Wonsulting Logo
Memorang Logo
Flourish Logo
Climb Together Logo
Design Works Logo
Lge Logo
Woven Logo
Softbank Logo
Humana Logo
Aecho AI Logo
Betteryou Logo
Nestwork Logo
Innovax Systems Logo
Jammy Chat Logo
Aura Health Logo
Wonsulting Logo
Memorang Logo
Flourish Logo
Climb Together Logo
Design Works Logo
Lge Logo
Woven Logo
Softbank Logo
Humana Logo
Aecho AI Logo
Betteryou Logo
Nestwork Logo
Innovax Systems Logo
Jammy Chat Logo
Aura Health Logo
Wonsulting Logo
Memorang Logo
Flourish Logo
Climb Together Logo
Sentra Logo
Althea Logo
Study Fetch Logo
Tone AI Logo
Thumos Logo
Ream Logo
New Computer Logo
Everfriends AI Logo
Mynd Logo
Pressmaster AI Logo
Nancy AI Logo
Parrot Prep Logo
Stimuler Logo
Quantanite Logo
University of Zurich
Sentra Logo
Althea Logo
Study Fetch Logo
Tone AI Logo
Thumos Logo
Ream Logo
New Computer Logo
Everfriends AI Logo
Mynd Logo
Pressmaster AI Logo
Nancy AI Logo
Parrot Prep Logo
Stimuler Logo
Quantanite Logo
University of Zurich
Sentra Logo
Althea Logo
Study Fetch Logo
Tone AI Logo
Thumos Logo
Ream Logo
New Computer Logo
Everfriends AI Logo
Mynd Logo
Pressmaster AI Logo
Nancy AI Logo
Parrot Prep Logo
Stimuler Logo
Quantanite Logo
University of Zurich

Resources

Reg (1)

What is emotion science?

How can artificial intelligence achieve the level of emotional intelligence required to understand what makes us happy? As AI becomes increasingly integrated into our daily lives, the need for AI to understand emotional behaviors and what they signal about our intentions and preferences has never been more critical.

Learn more
Expuni

Are emotional expressions universal?

Do people around the world express themselves in the same way? Does a smile mean the same thing worldwide? And how about a chuckle, a sigh, or a grimace? These questions about the cross-cultural universality of expressions are among the more important and long-standing in behavioral sciences like psychology and anthropology—and central to the study of emotion.

Learn more
introducing-voice-control-square

Introducing Voice Control

We’re introducing Voice Control, a novel interpretability-based method that brings precise control to AI voice customization without the risks of voice cloning. Our tool gives developers control over 10 voice dimensions, labeled “masculine/feminine,” “assertiveness,” “buoyancy,” “confidence,” “enthusiasm,” “nasality,” “relaxedness,” “smoothness,” “tepidity,” and “tightness.” Unlike prompt-based approaches, Voice Control enables continuous adjustments along these dimensions, allowing for precise control and making voice modifications reproducible across sessions.

Learn more

00/00