EVI 3: Understand and generate any voice - Hume AI's new voice that truly understands emotion
Hume AI's EVI 3 is a new speech-language model for highly expressive, realistic & emotionally intelligent voice AI. Generates any voice/personality from prompts. Outperforms GPT-4o in empathy & naturalness.
Replies
Hi everyone!
Most voice AI today, even the good ones, can still feel a bit generic. They might sound clear, but often lack true personality or a deep sense of emotional connection. Hume AI is tackling this head-on with their new third-gen speech-language model, EVI 3.
EVI 3 offers truly personalizable voice AI. It isn't stuck with a handful of standard voices, it can generate any voice and personality you describe with a prompt. This means interactions can feel much more unique and expressive, as the same underlying intelligence handles understanding you and crafting a spoken response.
Hume AI's blind comparison results suggest it delivers on that human-like quality, with EVI 3 rated higher than GPT-4o on empathy, expressiveness, and naturalness. It also has a neat "fast and slow thinking" ability, connecting to reasoning models and web search as it talks.
You can try EVI 3 now through their live demo and an iOS app (API access is coming). It's a compelling step towards voice AI feeling less like a tool and more like a genuine interaction.
Absolutely love the mission behind Hume! It's so refreshing to see a company prioritizing emotional well-being in the AI space. Building technology that aligns with human values and goals isn't just important—it’s essential. Excited to see how Hume shapes the future of emotionally intelligent AI. Keep up the amazing work!
Hume AI
@supa_l Thanks! We’re excited about what’s ahead.
Sounds outstanding!! Incredibly natural-sounding voice. Amazing job, team!
Hume AI
@sahithkrishna_an Thank you!
Pressmaster.ai
EVI is just incredible. It has been part our Tool since day one and users love it. Great job guys!
Hume AI
@alex_petrisor2 Thanks, Alex!
Hume AI
Hi everyone! Really excited that we can share what we have been building recently. EVI 3 is another step toward general voice intelligence. It is a speech-language model that can understand and generate any human voice, not just a handful of speakers. With this broader voice intelligence comes greater expressiveness and a deeper understanding of tune, rhythm, timbre, and speaking style.
Leave a comment with your favorite voice designs!
Wild to see how far voice AI has come - EVI 3 really does feel like a leap! Generating any voice and personality, especially with this kind of emotional nuance and style control, is next-level. The thoughtful work from this team of exceptional humans just keeps raising the bar. Psyched to see what's next and can’t wait to get building - I know our users are going to love it.