New York startup Hume has launched EVI 3, an advanced conversational AI model that lets users create custom synthetic voices through voice-to-voice interaction. The technology targets applications from customer support to virtual companionship, according to reporting by Carl Franzen for VentureBeat. Users can specify personality traits, vocal qualities, and emotional tones to generate voices ranging from warm guides to quirky narrators. Internal testing with 1,720 users showed EVI 3 outperformed OpenAI’s GPT-4o voice model across categories including naturalness, expressiveness, and empathy. The system offers 300-millisecond response times and supports English and Spanish. While currently available through a live demo, developer API access will launch in coming weeks with usage-based pricing. Unlike competitors such as ElevenLabs, EVI 3 currently lacks voice cloning capabilities, though Hume plans to add this feature to its separate Octave text-to-speech model.