Rainbow's Bedtime Problem - Audio Book
Rainbow Dash has to stay over at Twilight's house, but she gets more than she bargained for when Twilight makes her wear something to keep visits to the laundry room minimal.
So a few months back I was informed of this new thing called Fifteen.AI, a website where you can use a neural network to generate speech from text that sounds very natural. I got inspired to create a short audio story, and might do more in the future if you guys like this one. I hope you enjoy it!
Cover art by "mlpcutepic"
So a few months back I was informed of this new thing called Fifteen.AI, a website where you can use a neural network to generate speech from text that sounds very natural. I got inspired to create a short audio story, and might do more in the future if you guys like this one. I hope you enjoy it!
Cover art by "mlpcutepic"
Category Music / Baby fur
Species Pony
Gender Female
Size 120 x 91px
Thank you!! :D I've got some ideas in mind, and I'll probably put them together soonish. :)
Fantastic! I hope to see more!! <3
I love how you even have the ending credits song even though it's completely pointless! XD
I love how you even have the ending credits song even though it's completely pointless! XD
this is adorable please do more id love to hear more story with this it sounds great.
I'm definitely thinking about some other possible storylines involving the other cast members. :)
"say that again and i'll stuff it down your throat"
I died lmao
I died lmao
Lol, when the neural network generated that particular reading, I had to stop generating dialogue in order to laugh my butt off. XD I *knew* I had to use that one!
It's sort of scary how well that AI did this... It sounds a little off, like I can tell it's not real voices, but my guess would have been some kind of voice modulation not AI generated. I might have to check it out just to play around with!
You might be interested to know that Fifteen.ai was funded in 2017 by MIT's Computer Science and Artificial Intelligence Laboratory, which is when the neural network began to learn how to talk correctly. It was then fed an hour or so of voice samples from Twilight Sparkle at first in order to generate her voice and can now say any phrase, not just lines from the show (notice how many words in my work have no origin from the show itself). This represents a significant advance in machine learning, because voice synthesis normally takes hours upon hours of recorded dialogue to learn how to speak, and also required a monotone voice to establish a baseline. They would use audio books to get the voice samples, as you could get tons of dialogue as well as an established script to teach the neural network how to do it. Fifteen.ai is able to do the same thing with less than an hour of dialogue, which is mind-blowing!
Wait so it was fed voice lines from MLP as it's original learning, or you fed it lines so it could do that voice? It's pretty amazing it can replicate a voice with so little to work from though, neat but also kind of scary.
The guy who created it put in lines from the show for it to learn, then inputted a transcription of that line so that the neural network had a baseline for what each syllable is in text form. Then it simply ran hundreds of permutations, with the guy who made it giving it a pass or fail on how it pronounced them. Once it learned how to do lines from the show, it was then able to learn other words. I'm not sure exactly how it works, but the neural network is pretty great at generating dialogue.
if only the guy behind fifteen knew what he's unleashed upon this earth
So we need the conclusion to the story we need to know what happened it was awesome
You need to make more like a comic or like continuing the story that'll be cool
You need to make more like a comic or like continuing the story that'll be cool
I don't think I'll be continuing this story as it already has a beginning, middle, and end. But I'll probably do more audio books once the new version of Fifteen.AI has been sorted out. I reads the lines WAY too quickly now, so it doesn't sound as natural despite not having a robotic tone anymore.
Well, I'm on the site right now—but I'm not having any luck generating what I type into it. No matter what I do, all I'm getting is an "Error code 422: Invalid arguments". What gives?
It's possible that the site is acting up, since he's had server issues in the past. You can ask the creator directly on Twitter about the issue and he should be able to provide an answer.
I tried it after several "Invalid arguments" errors, and it began working correctly. Keep working on it and it should be fine.
I recorded it over the dialogue, and I'm not sure how to extract it.
It's an Audacity file, so I'm sure you could work with that. Also, maybe DM me so I can send it to you?
Yeah, just type "fifteen.ai" into your web browser. It'll take you right there.
Thanks! I hope to make another one eventually. I have an episode-length script written, but it's only the first draft and needs some polishing before I can consider starting another one of these.
Comments