New best story on Hacker News: Show HN: Three new Kitten TTS models – smallest less than 25MB

Show HN: Three new Kitten TTS models – smallest less than 25MB
439 by rohan_joshi | 162 comments on Hacker News.
Kitten TTS ( https://ift.tt/MbvNAFU ) is an open-source series of tiny and expressive text-to-speech models for on-device applications. We had a thread last year here: https://ift.tt/LExbUqP . Today we're releasing three new models with 80M, 40M and 14M parameters. The largest model (80M) has the highest quality. The 14M variant reaches new SOTA in expressivity among similar sized models, despite being <25MB in size. This release is a major upgrade from the previous one and supports English text-to-speech applications in eight voices: four male and four female. Here's a short demo: https://www.youtube.com/watch?v=ge3u5qblqZA . Most models are quantized to int8 + fp16, and they use ONNX for runtime. Our models are designed to run anywhere eg. raspberry pi, low-end smartphones, wearables, browsers etc. No GPU required! This release aims to bridge the gap between on-device and cloud models for tts applications. Multi-lingual model release is coming soon. On-device AI is bottlenecked by one thing: a lack of tiny models that actually perform. Our goal is to open-source more models to run production-ready voice agents and apps entirely on-device. We would love your feedback!

New best story on Hacker News: “Your frustration is the product”

“Your frustration is the product”
494 by llm_nerd | 300 comments on Hacker News.

New best story on Hacker News: Google details new 24-hour process to sideload unverified Android apps

Google details new 24-hour process to sideload unverified Android apps
513 by 0xedb | 602 comments on Hacker News.
https://ift.tt/MSbNu20...

New best story on Hacker News: Warranty Void If Regenerated

Warranty Void If Regenerated
487 by Stwerner | 297 comments on Hacker News.
As an experiment I started asking Claude to explain things to me with a fiction story and it ended up being really good, so I started seeing how far I could take it and what it would take to polish it enough to share publicly. Over the last couple months, I've been building world bibles, writing and visual style guides, and other documents for this project… think the fiction equivalent of all the markdown files we use for agentic development now. After that, this was about two weeks of additional polish work to cut out a lot of fluff and a lot of the LLM-isms. Happy to answer any questions about the process too if that would be interesting to anybody.

New best story on Hacker News: Python 3.15's JIT is now back on track

Python 3.15's JIT is now back on track
474 by guidoiaquinti | 291 comments on Hacker News.

New best story on Hacker News: Nightingale – open-source karaoke app that works with any song on your computer

Nightingale – open-source karaoke app that works with any song on your computer
492 by rzzzzru | 145 comments on Hacker News.

New best story on Hacker News: Every layer of review makes you 10x slower

Every layer of review makes you 10x slower
557 by greyface- | 310 comments on Hacker News.