Search

Vui Nano — a small, context-aware text-to-speech model trained on real conversations. 219M active params (305M total), Apache 2.0, voice cloning, streaming, runs on CPU (dependency-free C build). Ships with a full real-time voice assistant: WebRTC, ASR, local LLM, OpenAI Realtime API compatible.

Declarative, component-based UI library for Emacs. React-like components with state, hooks, reconciliation, and layouts - rendered using native Emacs widgets.