LuxTTS: open-source voice cloning at 48kHz, 150x realtime, under 1GB VRAM
tom_doerr · x · 2026-09-11
LuxTTS, a lightweight ZipVoice-based TTS project (5.3k GitHub stars), delivers SOTA voice cloning on par with models 10x larger.
- Quality: clear 48kHz speech, vs 24kHz limits of most TTS models
- Speed: 150x realtime on a single GPU, faster than realtime on CPU
- Efficiency: fits within 1GB VRAM, runs on any local GPU
Supports CUDA, CPU and macOS MPS; simple pip install and a few lines to load and infer, with Colab and Spaces demos available.
More from Infra
- SemiAnalysis: OpenAI reportedly negotiating ~1GW TPU commitment while seeking sites — dylan522p · 2026-10-28
- I tested 11 video upscaling methods for AI video: local, Topaz and cloud compared — lopas99 · 2026-10-28
- Thermo-backed CTO says AI is in its dial-up phase, touts disaggregated compute for an ultrafast 'broadband moment' — beffjezos · 2026-10-28
- DeepSeek-V4.1-Flash Q2 runs at 41 tok/s on one RTX 3090, 90% token match vs API — musicurgy · 2026-10-28
- USearch v3 RC ships after 1,000 days, its libraries now embedded in 550K-star projects — viglovikov · 2026-10-28
- SK Hynix says memory demand will outpace supply through 2030 — Chemical_Hawk_6307 · 2026-10-28