Replying to Avatar lemon

So text to speech would be listening to Kind 5250, then post Bolt11 to Kind 7000 as feedback for payment required and then, finally, once paid post desired content (.wav file) to Kind 6250, right?

I THINK I got it running so try it out and let me know. 🤞

I set pricing to $0.01 for testing, but it will have a dynamic quote option if works out.
Avatar
PABLOF7z 2y ago

Yeah, that’s one flow. The important part is that you accept events as inputs so if I create a 5250 with

[ i, “event-id”, “event” ]

You fetch event-id and use that content as the text to be processed

That way i can:

* create a nostr content discovery event

-> output of that is 50 or 100 e tags of interesting events

* create a summarization job that takes those 50 or 100 events as input and creates a single summarization content

* create a 5250 that reads me the summarization in guy swann’s voice

Reply to this note

Please Login to reply.

Discussion

Avatar
lemon 2y ago

That’s how I have it. It’s looking for input “event” tags. 😊

Cool idea, let me know if it works on your side.

Avatar
lemon 2y ago

Are you just using Vendata.io to run that string of jobs? Or do you have another tool?

I haven’t seen any other clients that make use of DVMs yet. 😔