I just listened to this AI generated audiobook and if it didn’t say it was AI, I’d have thought it was human-made. It has different voices, dramatization, sound effects… The last I’d heard about this tech was a post saying Stephen Fry’s voice was stolen and replicated by AI. But since then, nothing, even though it’s clearly advanced incredibly fast. You’d expect more buzz for something that went from detectable as AI to indistinguishable from humans so quickly. How is it that no one is talking about AI generated audiobooks and their rapid improvement? This seems like a huge deal to me.
I would guess there is a LOT of work going into each voice. Playing with different parameters and prompts. I don’t think it’s as simple as just copying the text into a box. Not yet at least :)
That’s a good thought there though. Audiobooks could have each character voiced uniquely.
This is literally the only upside I see from this.
One of the Dune audio books started off as multiple voices and then part way through it was finished by just one guy. Really impressed with it at first, and then really kind of debuffed by it. I had already read the book years before so it wasn’t a big deal, but like wtf?
Lol what a troll audio book.
I can hope! With the speed things are developing it may not be too long.
I haven’t played around with or looked into much to do with AI at all but would be willing to put in some time into playing with prompts / parameters if it meant I could eventually create a reliable work flow to create things such as what I mentioned.
I think I’ll have to do some research, I need some more old school hollow earth stories in my life xD
I don’t see why you couldn’t give a few examples and then grab the dialog of a person in along with their description (or just the whole book) and get the llm to generate the prompt for you