https://www.youtube.com/watch?v=GuJKTodX1FA [Embed]

The voices in this video were generated by an AI model trained using audio samples. We have 8 (soon to be 9) seasons worth of audio material from My Little Pony, all of which are in surround sound with an isolated voice channel.

I propose to you that we use this technology to create accurate text to speech voices for the Mane 6 (or any other pony with enough audio material to work with). You don't have to think long to imagine the possibilities although knowing you guys it will be for waifus. Is there anyone else here who wants to make this happen?

was it ever actually good?

do you think that black gryphon still clops to sweetie belle now that he is (openly) dating her voice actor?
do you think he asks her to do the voice?
do you think she does it just to fuck with him?

>Vogel is making an LGBTQ show

If MLP had a 10th season, what kind of SJW nonsense would we have in the episodes?

For all you metafags, which I'm sure exist among the tulpafags, I've had a theory for quite some time about how one could legitimately go to Equestria, including any headcanon, OCs, personality changes, or really anything you could imagine being functionally cohesive. I'm bored and don't care enough about any shitstorm this might cause, so here it is.

For this to work, you'll at least have to be open-minded. Even if you don't believe in the metaphysical stuff, I encourage you to read anyway (skimming over the new agey stuff, of course), since it could still yield benefits even if it doesn't work.

The theory revolves around the practice of astral projection, the fairly common practice whereby the practioner purportedly leaves his/her body to explore other realms of existence known collectively as the "astral plane." The astral plane could be described as a lucid dream on steroids, where you can meet others and find spirits. as well as a bit of multiversal theory. The multiverse is the collection of anything that you could possibly imagine with any configuration, laws of physics, or lack thereof, and more. It encompasses everything from the alternate timeline where you DIDN'T spaghetti your brains out in front of that girl last week, to places like Equestria, to a reality literally made of color.

Alright, now that that's out of the way, the basic idea is to first achieve astral projection (which can be difficult, depending on who you are), imagine yourself in the Equestria you want (making sure you're not going to a "tulpa reality" (a reality you create in the astral plane, like a tulpa, but it's a place), then using one of several techniques to enter that reality semi-permanently.

Post ponies, no copypasta. The finale sucked.

The comics are decent.

The manga is really good.

The wiki for all your fandom needs: https://mlp.fandom.com/wiki/My_Little_Pony_Friendship_is_Magic_Wiki

Hey guys, get off your Commodore 64s for a second and check this out...did anybody catch that new cartoon that aired the other day? My Little Pony, I think it was called. I recorded it on Betamax (Yeah I know) and then transferred it to VHS so you could check it out!

https://www.youtube.com/watch?v=O-Ll5zaPcIE

What do you guys think? I don't think this is gonna be another Cabbage Patch Kids...I kinda like the flying one, she's pretty cool!

TwAIlight welcomes you to the Pony Voice Preservation Project!
https://clyp.it/qrnafm4y

This project is the first part of the "Pony Preservation Project" dealing with the voice.
It's dedicated to save our beloved pony's voices by creating a neural network based Text To Speech for our favorite ponies.
Videos such as https://youtu.be/GuJKTodX1FA. or https://youtu.be/DWK_iYBl8cA have proven that we now have the technology to generate convincing voices using machine learning algorithms "trained" on nothing but clean audio clips.
With roughly 10 seasons (9 seasons and 5 movies) worth of voice lines available, we have more than enough material to apply this tech for our deviant needs.

https://derpy.me/PHsCn

Any anon is free to join, and many are already contributing. Just read the guide to learn how you can help bring on the wAIfu revolution. Whatever your technical level, you can help.
Document: https://docs.google.com/document/d/1xe1Clvdg6EFFDtIkkFwT-NPLRDPvkV4G675SUKjxVRU

We now have a working TwAIlight that any Anon can play with:
https://derpy.me/vCzm2 (Training)
https://derpy.me/hdJQF (Synthesis)
https://derpy.me/YTJ94 (Guide)

>Active Tasks
Create a dataset for speech synthesis (https://youtu.be/KmpXyBbOObM)
Test some AI program with the current dataset
Finalise dataset
AI Training/Interface/Refinement
Littlepip voices
Dan vs dataset

>Latest Developments
https://clyp.it/xp4q1bru [Yay!]
Anons are investigating Deepvoice3, Tacotron2 with GSTs, SV2TTS, and Mellotron
Anypony can now train on Google Colab
Dr. Who dataset done
Clipper looking for work, inquire below ^:)
15.ai

>Voice samples (So far)
https://derpy.me/3TBK4
https://derpy.me/fHs3K
https://derpy.me/O1xdh

>Clipper Anon's Master File 2.0:
https://mega.nz/#F!L952DI4Q!nibaVrvxbwgCgXMlPHVnVw
https://derpy.me/6im1i (torrent)

>Synthbot's Torrent Resources
https://derpy.me/ZJNca

>Cool, where is the discord/forum/whatever unifying place for this project!?
You're looking at it.

Last Thread:
>>35058606

Welcome back to 2012-2013, you fucking memelord.

The 2s gets are almost upon us!

What will it be?!