Zonos3-Mini Voice-Cloning TTS Hits SGLang-Omni: 57ms First Audio on One H100
spikedoanz · x · 2026-11-10
ZyphraAI's Zonos3-Mini voice-cloning TTS model runs on SGLang-Omni from day 0. It's an 800M-parameter MoE with 80M active parameters per token, streaming first audio in just 57 ms on a single H100 — well suited for real-time, low-cost voice deployments.
More from Infra
- Chrome 153 ships native tab recorder: 120fps 4K AV1 capture, no ffmpeg needed — Vjeux · 2026-11-10
- AI compute cumulative spend must grow 5-10x vs cloud before oversupply, says LeClerc — robleclerc · 2026-11-10
- AWS EKS now offers per-Pod hardware isolation with Nitro Sandbox — tekbog · 2026-11-10
- simdjson disables 256-bit LASX on Loongson 3A6000: 128-bit LSX is 6.7% faster — lemire · 2026-11-10
- Vera launches gyms, benchmarks and agents for cloud infrastructure operations — tianyin_xu · 2026-11-10
- NVIDIA paper: masking ~10 'intrusion heads' recovers 57% of distractor accuracy loss — rohanpaul_ai · 2026-11-10