Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model

Re:Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model by lynx97 on Wednesday August 06, 2025 @04:56AM (#44809552)

Debian pretty much "solved" this by making pip refuse to install packages if you are not in an venv.

[ Parent | on HN ]

Re:Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model by gm678 on Wednesday August 06, 2025 @06:04AM (#44810036)

It needed distro buy in and implementation, but this is from the Python side: https://peps.python.org/pep-0668/

[ Parent | on HN ]

Re:Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model by auscompgeek on Wednesday August 06, 2025 @06:06AM (#44810054)

IIRC that's actually a change in upstream pip.

[ Parent | on HN ]

Re:Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model by ChickeNES on Wednesday August 06, 2025 @05:47AM (#44809914)

Ditto OpenSUSE, at least on Tumbleweed

[ Parent | on HN ]

Re:Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model by 77pt77 on Wednesday August 06, 2025 @06:26PM (#44818582)

Well, with my python 3.13.5 not even that works!

Pretty impressive but this seems to be a staple of most AI/ML projects.

"Works on my machine" or "just use docker", although here the later doesn't even seem to be an option.

[ Parent | on HN ]