Kitten TTS is an open-source series of tiny and expressive text-to-speech models for on-device applications. We are excited to launch a preview of our smallest model, which is less than 25 MB. This model has 15M parameters.<p>This release supports English text-to-speech applications in eight voices: four male and four female. The model is quantized to int8 + fp16, and it uses onnx for runtime. The model is designed to run literally anywhere eg.  raspberry pi, low-end smartphones, wearables, browsers etc. No GPU required!<p>We&#x27;re releasing this to give early users a sense of the latency and voices that will be available in our next release (hopefully next week). We&#x27;d love your feedback! Just FYI, this model is an early checkpoint trained on less than 10% of our total data.<p>We started working on this because existing expressive OSS models require big GPUs to run them on-device and the cloud alternatives are too expensive for high frequency use. We think there&#x27;s a need for frontier open-source models that are tiny enough to run on edge devices!

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

Claude Code IDE integration for Emacs

We replaced passwords with something worse

Automerge 3.0

Jules, our asynchronous coding agent

Litestar is worth a look

Project Hyperion: Interstellar ship design competition

Writing a Rust GPU kernel driver: a brief introduction on how GPU drivers work

A fast, growable array with stable pointers in C

Rules by which a great empire may be reduced to a small one (1773)

Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs

The Bluesky Dictionary

We'd be better off with 9-bit bytes

Multics

Mac history echoes in current Mac operating systems

Cracking the Vault: How we found zero-day flaws in HashiCorp Vault

"I closed MPEG on 2 Jun '20 when I left because obscure forces had hijacked it."

A candidate giant planet imaged in the habitable zone of α  Cen A

Debounce

Herbie detects inaccurate expressions and finds more accurate replacements