←back to thread

Show HN: AI toy I worked on is in stores

(www.walmart.com)
156 points Sean-Der | 2 comments | 12 Oct 25 14:15 UTC | HN request time: 0s | source

Alt link: https://mrchristmas.com/products/santas-magical-telephone

Video demo: https://www.youtube.com/watch?v=0z7QJxZWFQg

The first time I talked with AI santa and it responded with a joke I was HOOKED. The fun/nonsense doesn't click until you try it yourself. What's even more exciting is you can build it yourself:

libpeer: https://github.com/sepfy/libpeer

pion: https://github.com/pion/webrtc

Then go do all your fun logic in your Pion server. Connect to any Voice AI provider, or roll your own via Open Source. Anything is possible.

If you have questions or hit any roadblocks I would love to help you. I have lots of hardware snippets on my GitHub: https://github.com/sean-der.

Show context
architectonic ◴[13 Oct 25 22:30 UTC] No.45574021[source]▶
How much computing power would one need to get this working completely local running a half decent llm fine tuned to sound like santa with all tts, stt and the pipecat inbetween?
replies(4): >>45574195 #>>45575432 #>>45576228 #>>45583058 #
oofbey ◴[14 Oct 25 01:56 UTC] No.45575432[source]▶
More than you can physically fit in a phone like that. Many hundreds if not thousands of watts of GPU.
replies(2): >>45575717 #>>45575785 #
margalabargala ◴[14 Oct 25 02:43 UTC] No.45575717[source]▶
That's not true. You could run such an LLM on a lower end laptop GPU, or a phone GPU. Very low power and low space. This isn't 2023 anymore, a Santa-specific LLM would not be so intensive.
replies(2): >>45575967 #>>45586091 #
oofbey ◴[14 Oct 25 03:31 UTC] No.45575967[source]▶
But on that compute budget it’s gonna sound so stupid. Oh right. Santa.
replies(1): >>45576475 #
1. margalabargala ◴[14 Oct 25 05:10 UTC] No.45576475[source]▶
It's a children's toy, how nuanced does its responses need to be?
replies(1): >>45597473 #
2. oofbey ◴[15 Oct 25 19:46 UTC] No.45597473[source]▶
I agree. It just took me a while to figure it out. A 3B param LLM would do perfectly well.