FrankenTTS: pure-Rust Qwen3-TTS port runs voice cloning entirely in your browser
BLUECOW009 · x · 2026-09-05
FrankenTTS is a clean-room, pure-Rust port of Qwen3-TTS-12Hz-0.6B with no Python, PyTorch, GPU, or server — compiled to WebAssembly and running fully in the browser:
- 1.4–1.6× real time as native CLI; 0.31–0.43× in-browser; all 28 layers verified
- Zero-shot voice cloning; recordings pass a neural denoiser (ported FastEnhancer) before becoming a 4KB speaker vector, then discarded
- 1.77 GB model fetched with pinned SHA-256 checks into private browser storage; nothing leaves your device
A live demo runs in-tab, and it's being called the best local TTS option for Mac.
More from Infra
- llama.cpp team launches Llama: one-click local AI on your Mac menu bar — Hugging Face · 2026-10-23
- China's daily token use hits 500T, up 4x as average price doubles to ¥13.46 — teortaxesTex · 2026-10-23
- New all-reduce kernels deliver 12% decode speedup for DeepSeek-V4.1 on PCIe-connected GPUs — AlpinDale · 2026-10-23
- Offshore oil rigs could be converted into AI data centers powered by stranded gas — clemnt · 2026-10-23
- Same native UI, two stacks: Swift build is ~80MB Mac-only, Zig build is ~10MB cross-platform — jedisct1 · 2026-10-23
- SurfSense: an open-source local NotebookLM with MCP agents and a prompt-caching lesson — FurtiveMirth · 2026-10-23