Kyutai shrinks Pocket TTS to 1.9M params, running 103x real-time on one CPU core
alexcovo_eth · x · 2026-10-21
Kyutai Labs released smaller versions of Pocket TTS: from the original 100M parameters down to an 18.2M model matching the original's quality, a 6.9M model, and a 1.9M model that runs 103x faster than real time on a single CPU core — all with voice cloning, dramatically lowering the bar for local high-quality TTS.
More from Infra
- Robotics startup launches Deployments to serve fine-tuned HF checkpoints to robots in real time — arnie_hacker · 2026-10-21
- ByteDance, Alibaba, Tencent order 3M+ Nvidia RTX PRO 5500 cards worth $35B, Reuters reports — SumitGup · 2026-10-21
- TorchTPU demo: unified vLLM & SGLang backend for LLM serving on TPUs — Rob_Mulla · 2026-10-21
- Google, Red Hat release llm-d 1.0: open K8s-native distributed inference stack — rseroter · 2026-10-21
- acs infra launches free base model API offering Llama 3.1 8B and 405B for LLM psychology researchers — amplifiedamp · 2026-10-21
- Developer Moves AI Agents to a Dedicated Linux Workstation Using Incus System Containers — kevinkern · 2026-10-21