Kitten TTS: 25MB CPU-Only, Open-Source Voice Model

Re:Kitten TTS: 25MB CPU-Only, Open-Source Voice Model by kamranjon on Tuesday August 05, 2025 @11:07PM (#44807170)

The best open one I've found so far is Dia - https://github.com/nari-labs/dia - it has some limitations, but i think it's really impressive and I can run it on my laptop.

[ Parent | on HN ]

Re:Kitten TTS: 25MB CPU-Only, Open-Source Voice Model by wkat4242 on Wednesday August 06, 2025 @08:30PM (#44819406)

Thanks I'll try! I like how it sounds, the quality is really good. But the limitations are really severe (shorter than 5 seconds is not ok, > 30 seconds is not ok, it will play a random voice every time, those make it pretty much unusable for an assistant to be honest).

But it might be worth setting it up and seeing if it improves over time.

[ Parent | on HN ]

Re:Kitten TTS: 25MB CPU-Only, Open-Source Voice Model by kamranjon on Thursday August 07, 2025 @10:13AM (#44824710)

You can get consistent voice by providing a sample - and yea the timing stuff is what you have to work around - have to basically chunk your inputs.

[ Parent | on HN ]