[–] 6 points 2 weeks ago (4 children)

I just set two of these up. I'm not a HA guy so my HA server only has these assistants, my Sonos system, and Music Assistant set up.

I'm still fussing through setting up tasks, but it's slowly turning into Alexa Jarvis.

I have it set up to play, pause/stop music from music assistant with a really hacky yaml script.

It can tell me the weather forecast.

That's all local processing with Whispr(stt) and Piper (tts).

For those who want the "tell me the tallest mountain in the world" type of support, the answer is cloud llms. I tried ollama on my PC, but it's just too slow. I have an opencode go subscription and that works pretty well with deepseek-v4-flash. You can also use a standard open ai api key with one of the nano or micro models.

It works, not quite as good as Alexa, but it's not bad.

  • source
  • [–] 7 points 2 weeks ago

    Great question! You use the Tailscale clients which are fully open source. Headscale is compatible with them, and if TS gets sketchy (which, very well may happen), those clients would need a fork.

    Tailscale's network is with paying for it you need enterprise features and they do have a free tier. I'm not going to lock myself in there though and prefer a full FOSS option.

  • source
  • parent
  • context
  • [–] 14 points 2 weeks ago (2 children)

    Fun fact none of you probably care about: I finally set this up last weekend.

    I really like it so far for keeping my phone sync'd up with my self hosted services. In the past I needed to flip between public and internal address if I wanted to bypass routing traffic up to my vps while laying in a bed 20ft from my server. Now, tail/headscale handles that for me.

    Glorious.

  • source
  • view more: next ›