dexter VS ovos-personal-backend

I wrote a toy one which works well enough for me:

  https://github.com/iamsrp/dexter

You need a Raspberry Pi with respeaker microphone. Many assistants to install around - for example https://github.com/iamsrp/dexter and many more.

Whisper is a bit slow on RPI and not working well for short phrases. It is more focused on long transcription like podcasts. You can try Vosk instead https://github.com/alphacep/vosk-api

Simple weather service added:

  https://github.com/iamsrp/dexter/blob/master/service/weather.py

Trying out OVOS on my Mark II, and using the ovos-personal-backend on a docker container. I noticed that there is a ovos-backend-manager project and wernt to roll my own docker container for it, but noticed that it is already installed via the ovos-personal-backend Dockerfile https://github.com/OpenVoiceOS/ovos-personal-backend/blob/dev/Dockerfile

MycroftAI : Does seem to be going away - They are currently winding down operations. Apparently the local-only OpenVoiceOS personal backend will also work as a backend for Mycroft - that repo has a Dockerfile. I haven't used Selene or the OVOS personal backend but would sway towards the OVOS solution.

some great responses here already, if you want to verify what information is sent you can also install the mock-backend. the logs will show you exactly what is being sent.