little hemlock
Hey, I'm somewhat new to this but I've managed to set up my own local LLM (Qwen3) as conversation agent.
The response times are as expected (10ish seconds) and that's fine, but I'd love my Voice Assistant to let me know that it's thinking while it's doing so.
Essentially I would like to create the following automation:
"Hey Jarvis, (question)" -> STT -> IF command will not be executed locally, then a) continue as usual and b) also say "Getting your answer one moment".
Any pointers?