Kokoro-82M: tiny open-source TTS model runs on CPU with quality of far larger models
solyarisoftware · x · 2026-09-28
- Kokoro-82M by hexgrad is an open-weight TTS model with just 82M parameters, Apache-2.0 licensed, that runs comfortably on CPU while delivering audio quality comparable to much larger models.
- v1.0 (Jan 2025) was trained on only a few hundred hours of data using 1,000 A100 GPU hours; API market pricing is under $1 per million input characters (under $0.06 per hour of audio output).
- The author warns that third-party sites with "kokoro" in their domain (e.g. kokorottsaicom) are likely scams unaffiliated with the project.
More from Infra
- From 16GB to 128GB: A Local AI Hardware Journey — TheOyinbooke · 2026-09-28
- Liquid AI makes the case for edge agents: 350M-2.6B models with no per-token bill — JosephJacks_ · 2026-09-28
- Dev runs Bonsai 2 locally on Mac Studio to diff medication lists in 5.75 seconds — MaziyarPanahi · 2026-09-28
- $100 used Tesla P100 beats gaming GPU nearly 2x for local LLM inference — Mrinohk · 2026-09-28
- Open-weight 27B model hits ~580 tok/s on Mac, 505% over baseline in 3 days — TheMoonMidas · 2026-09-28
- Why Doesn't Nvidia Just Sell Tokens Itself? Ex-Nvidia Engineer: "Jensen Makes His Friends Billionaires" — rohanpaul_ai · 2026-09-28