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)→

Original post →

More from Models

Models channel →