[LocalMode] Open-mic streaming speech-to-text (useLiveTranscribe) with VAD-segmented utterances, plus a listen→plan→speak turn-taking assistant (useTurnTaker: Granite 4.0 350M plans, Kokoro speaks) selectable via a two-mode picker. VAD choice: the zero-download energy VAD (default) or a gated ~2MB Silero ONNX V
pnpm dlx shadcn@latest add "https://registry.directory/r/localmode-ai/ui/blocks/audio/live-transcription.json"