Just tried it on my laptop. It's pretty amazing. I gave it a 50 second clip of a friend speaking and in about 4 minutes it produced an audio clip in his voice with whatever words I wanted. I'm seriously impressed.

https://github.com/Zyphra/Zonos

How’s this compare to likes of Fish audio? Wish they support voice clone using longer audio tho .

Haven’t looked into this space for few months , but iirc, previously SOTA was like GPT VITS or something ?

This is the clear SOTA at the moment, even better than ElevenLabs in a technical sense, because you can specify emotion, speed, etc.