News for hackers. Stuff that matters.

A comment on Kitten TTS: 25MB CPU-Only, Open-Source Voice Model. Parent comment

Re:Kitten TTS: 25MB CPU-Only, Open-Source Voice Model by graemep on Wednesday August 06, 2025 @09:25AM (#44811675)
I am not sure even that is enough. You would really need to do a clean room reimplementation to be safe - for exactly the same reasons that people writing code write clean room reimplementations.
[ Parent | on HN ]
Re:Kitten TTS: 25MB CPU-Only, Open-Source Voice Model by K0balt on Wednesday August 06, 2025 @09:42AM (#44811914)
Yeah, the algorithms and program flow would have to be materially distinct to be really safe. Maybe switching language paradigms would get that for you in most cases? Js->haskell->js? Sounds like a nightmare lol.
[ Parent | on HN ]