I have been working on making WebRTC + Embedded Devices easier for a few years. This is a hackathon project that pulled some of that together. I hope others build on it/it inspires them to play with hardware. I worked on it with two other people and I had a lot of fun with some of the ideas that came out of it.
* Extendable/hackable - I tried to keep the code as simple as possible so others can fork/modify easily.
* Communicate with light. With function calling it changes the light bulb, so it can match your mood or feelings.
* Populate info from clients you control. I wanted to experiment with having it guide you through yesterday/today.
* Phone as control. Setting up new devices can be frustrating. I liked that this didn't require any WiFi setup, it just routed everything through your phone. Also cool then that they device doesn't actually have any sensitive data on it.
I see so much potential if I can make hardware hacking + WebRTC easy. Not just for AI assistants but security cameras + robotics. If anyone has questions/ideas/feedback here to help :)
You can use it to build lots of different real-time communication projects. Conferencing, Send your audio/video to GPU servers for AI, broadcasting and lots more.
It’s a super fun space to be in
https://www.youtube.com/watch?v=G5OUnpPAyCg
Even forgetting the main advantages (24x7 availability, and ability to talk about basically any topic for as much or little time as you want), they also get basically every obscure reference/analogy/metaphor and how it ties in to the topic at hand.
Usually when you're talking to another person, the intersection of obscure references you can confidently make (with the assumption your partner will understand them) is much more limited. I enjoy making those random connections so it's a real luxury to have a conversation partner that gets them all.
Another one is simply the time and attention they can bring to things a normal person would never have the time for. I'd not want to talk someone's ear off, unless I was paying them and even then, I don't want to subject someone to topics of only interest to myself.
(Edit: I suppose it's the final apotheosis of the atomised individual leaving all traces of community behind)
If I put these devices through out my house it would allow me to switch AI personalities by proximity.
You can also use the device without your phone. These devices are also very cheap. I think you could do audio only for around ~5$
https://gist.github.com/mgarratt/afb3b57a08e2eb2479eb6083a86...
https://www.xda-developers.com/ollama-ai-comparison-raspberr...
https://www.xda-developers.com/raspberry-pi-voice-assistant-...
https://www.youtube.com/watch?v=o1sN1lB76EA
Deleted Comment
I was tempted to put Erik Satie in the README video. Didn’t want to risk copyright issues