Hume AI's EVI 3 clones your personality, not just your voice
Hume AI just launched EVI 3, a new speech-to-speech model alongside updated TTS capabilities. Instead of stopping at voice cloning, the model captures speaking style and unique language patterns—what Hume calls "personality cloning." Why it matters: voice assistants are moving from just sounding like you to actually talking like you.
Voice cloning just took another step toward sounding a little too real.
Hume AI just launched EVI 3, its latest speech-to-speech model, alongside new updates to its text-to-speech system. The company is framing the shift as moving from simple voice cloning to full-on personality cloning.
Mimicking style, not just sound
Most voice cloners stop at matching pitch, tone, and vocal timbre. Hume claims its voice AI can now replicate not only how you sound, but also your speaking style and language patterns.
The new capability is officially available through Hume’s TTS tools and its freshly rolled out EVI 3 speech-to-speech model.
Why it matters
We think the conversational AI race is quickly shifting from raw speech latency to emotional and behavioral authenticity. Giving developers the ability to clone speaking quirks and conversational styles makes virtual agents feel far less scripted.
Hume’s focus on personality is clever, but cloning someone’s unique cadence and slang opens a whole new can of worms for impersonation and verification.
Sources (1)
- x.com(opens in a new tab)Originalx.com