Hanzo Huang's RK3576 stack uses Home Assistant's Wyoming protocol as a hard abstraction boundary to turn a Rockchip RK3576 board into a local voice backend for Home Assistant. Four containerized services handle the pipeline: openWakeWord detects the wake phrase (port 10400), Wyoming Whisper handles speech-to-text (port 10300), Wyoming Piper handles text-to-speech (port 10200), and Qwen 2.5 1.5B served via an RKLLM-backed OpenAI-compatible API handles open-ended conversation (port 8001). Huang reports per-stage timings for a typical smart-home command: Whisper transcription at 0.626 seconds, Piper synthesis at 0.474 seconds, and RKLLM response at 2.82 seconds. The RK3576 integrates a 6 TOPS dual-core NPU supporting INT4/INT8/FP16 inference. The hardware used is the Seeed Studio reComputer RK3576, paired with a reSpeaker XMOS XVF3800 microphone array. To deploy, clone the GitHub repo (github.com/Hanzo-Huang/rk3576-home-assistant-voice), run docker compose up -d --pull always, then add three Wyoming integrations in HA under Settings -> Devices & services -> Wyoming Protocol.