Remix clone Hacker News

This is quite cool. Two questions:

- why do you need nextjs frontend for what looks like a headless use case? - how much would be the OpenAI bill if there is 15 minutes of usage per day?

▲

irq-1 3 days ago | parent | next [-]

> This equates to approximately $0.06 per minute of audio input and $0.24 per minute of audio output.

https://openai.com/index/introducing-the-realtime-api/

About the nextjs site, I was thinking maybe its difficult to have supabase hold long connections, or route the response? I'm curious too.

	▲	akadeb 3 days ago \| parent [-]
		The long connections are ultimately handled by Deno Edge so the site isn't used there. The NextJS frontend (which also could be an iOS/Android app) helps provide an interface to select character, create AI characters, set ESP32 volume, and view conversation history.

▲

akadeb 3 days ago | parent | prev | next [-]

thank you! The nextjs frontend is to set things like device volume, selecting which character you are interacting with, viewing conversation history etc. I just tried it and for a 15 minute chat, it's roughly 20c. Roughly 570 input tokens

▲

JKCalhoun 3 days ago | parent | prev [-]

And I am wondering, why use an ESP32 if you don't need the WiFi? (And, please, no WiFi in a toy!)

	▲	akadeb 3 days ago \| parent [-]
		Currently we connect to a Wifi network to reach the Deno edge server. Some popular toys doing it: Yoto, Toniebox