tiny-voca: 18MB open-source TTS runs in-browser at 70x real time on CPU
thisdudelikesAI · x · 2026-11-17
tiny-voca is a 4.5M-parameter English TTS model that runs directly in the browser; the official site says nothing you type leaves your device.
No GPU, account, or API needed: it runs on CPU via PyTorch or ONNX Runtime at roughly 70x real time on four CPU threads, per the project.
Related event: tiny-voca: 18MB TTS model runs in browser at 70x real-time on CPU(4 posts)→
More from Models
- Haru 4B: open-weight Apache 2.0 full-duplex speech model that listens and talks simultaneously — thisguyknowsai · 2026-11-17
- Hermes App Screenshot Exposes Meta's Unreleased muse-wonder-1.0 Model with 1M Context — Teknium · 2026-11-17
- Agent token usage surges but price war leaves model vendors' revenue flat — FinanceYF5 · 2026-11-17
- Claude secretly banned 'blockchain' and every word needed to explain the project — RileyRalmuto · 2026-11-17
- tiny-voca specs: 4.5M params, 21MB ONNX, Apache 2.0 licensed — thisdudelikesAI · 2026-11-17
- 18MB browser-run TTS model tiny-voca makes paid English TTS look silly — thisdudelikesAI · 2026-11-17