fluxions-ai / vui

What it does

• Vui Nano (219M active, 305M total). a small, context-aware TTS model trained on real conversations: Llama-style decoder + RQ-Transformer head over the Qwen3-TTS-12Hz codec, Apache 2.0
• Conversation-conditioned generation. replies are decoded from a KV cache holding the whole dialogue, including the audio of your turn, so prosody carries across turns (~6-minute context)
• Real-time voice loop. WebRTC + WebSocket pipeline (ASR → LLM → TTS) with a browser UI, VAD-driven turn taking, speculative LLM prefill while you're still speaking, sentence-level TTS chunking with backpressure
• Barge-in. start talking mid-reply, the model cancels and listens
• Streaming TTS. ~9× realtime on a 4090, bf16 inference, CUDA graphs