Put transcription on the device before you tune the LLM.

Put transcription on the device before you tune the LLM. Tiny on-device STT runtimes like whisper.cpp let you keep audio local, which buys latency, privacy, and retention control and lets you send text or structured events to the cloud instead of raw audio. Use cloud speech as a fallback when accuracy or languages demand it, not as the default. Operational rule: try an edge-first pipeline and make remote STT an explicit, logged downgrade path.