A 4.5M-parameter TTS model runs 70x real-time on CPU and cost just $10 to train

mrkn1 42 points 3 comments November 18, 2026
huggingface.co · View on Hacker News

Discussion Highlights (2 comments)

ig-88ms

I was irritated by the childlike voice at first, but they acknowledge that they were aiming for a twenty something female voice and plan to build a more mature voice.

ilyaizen

Hi there. I made CopySpeech, a desktop app that reads copied text aloud. Copy the same text twice to hear it. The default voice is tiny-voca, a 4.5M-parameter model. In my tests, it starts speaking about 0.1 seconds after a warm start. I'm happy with how fast it is. Repo: https://github.com/ilyaizen/CopySpeech Site: https://copyspeech.ilyaizen.link/

Semantic search powered by Rivestack pgvector
13,334 stories · 126,150 chunks indexed