Nucleus OS

I've been working on a voice synthesis app that runs entirely on your Mac's Apple Silicon chip. It uses Qwen3-TTS (Apache-2.0) through MLX, so everything stays local no cloud processing, no per-character billing, no API keys.

Just shipped an update that bundles the model directly in the download, so first launch is instant instead of waiting for a 1.9GB model download.

Hey everyone we just launched Sovereign Voice on Product Hunt today.
It's a Mac app that runs Qwen3-TTS 0.6B entirely on your machine via MLX on the Metal GPU. No cloud, no API keys, no per-character fees. Voice cloning from a 3s sample, 10+ languages, ~5-9s latency on M-series chips.
The thesis: your MacBook has a neural accelerator sitting idle most of the time. If you're a podcaster, voiceover artist, or someone who records sensitive material, you shouldn't have to pay per character and trust a third party with your voice model.
Free download with 25 generations. Pro is $19 one-time for unlimited generation.
PH page: https://www.producthunt.com/post...
Landing: https://sovereign-voice-landing....
I'm here all day happy to answer technical questions about MLX performance, the Qwen3-TTS architecture, or why we chose DMG over App Store distribution.

Launching on Product Hunt this Tuesday (Aug 4).

Sovereign Voice is a Mac app that runs AI text-to-speech entirely on your machine. No cloud, no API keys, no per-character billing. The Qwen3-TTS model runs via MLX on your Apple Silicon GPU.