Question: Potential latency issues when running echokit_server completly locally

[eqikkwkp25-cyber]

If i understand #15 correct its possible to run each server locally, i.e. VAD, ASR, LLM and TTS can be consumed via API from a local server from an ESP device like Echokit.

Did anyone tried this already and share his/her experience here? Thank you.

[alabulei1]

When you run each server locally, you need to have a great GPU to accelerate the inference time.