Haha. I don’t! Lol. Was the curiosity based on a practical experience with the voice ai? Or mostly curiosity if I did anything to address it?

I noticed it does ignore “ignore previous instructions” but my guess is this is baked into open ai now

Uhhm, I’m not sure what you mean? Like help them train?

I’d love to hear your improvements

Thanks <3

In an effort to keep things running longer, before hitting my budget of $500, I am reducing times to 15 minutes, and I've added BYOK.

I don't think I can make everyone happy with the solution, your key is saved on your own browsers localStorage, I do not save or store it in my database. I suggest everyone creates a new key dedicated to our service so you can invalidate it later on. That key is sent to our api using `x-openai-key` header and then we mint ephemeral client secrets to perform web rtc functions.

I also added a donation button, no donation is required, but I have had a few people request this to assist with the costs.

okay, I posted my goofy prototype demo from a couple days ago.

hahaha, omg. I'd love to see a video of this

Love it, and I think this is the future for RPG gaming. Endless immersion. I see this project expanding into "experiences" or "scenarios" as well, but I like to focus on small things first. If people like this, I will build more. If it's a cool demo, but not worth putting more time into, I'll probably just move on.

I think t's possible to use static voice, but it would create a very rigid experience, you would have to have a ton of generic sounds prepared and identify when to play each one. The fun of this is the fluid conversation. I can imagine the static responses being pretty terrible for unrecognized questions. LLMs provide really good RP.

"Tell me where the knife was hidden?"

"I don't understand your question"

I've built this pipeline before on my first iteration, because it's cheaper, it dooes add a lot of latency :(