Replacing my tts with kasane teto
@tay ive had thoughts about using speach to text and then using teto to turn that text to speach but i keep putting it off because i dont know if software to do that exists or if i have to make it,,
@Tiny me neither, I was just shitposting unfortunately
VOICEPEAK | 重音テト(かさねてと)オフィシャルサイト

重音テトのオフィシャルサークル「ツインドリル」が運営する公式サイトです。

VOICEPEAK | 重音テト(かさねてと)オフィシャルサイト
@tay sadly it costs money :'(
スターターガイド (日本語)

Open singing synthesis platform / Open source UTAU successor - stakira/OpenUtau

GitHub
@tay hehehe :3c using the new tay search engine :3c
@Tiny apparenty there exists something call utau, or it's sucessor, open utau which takes voicebanks to synthesize singing.
open utau seems to be a gui program, we presumably just want the synthesis library beneath it.
Getting Started

Open singing synthesis platform / Open source UTAU successor - stakira/OpenUtau

GitHub
@Tiny apparently that "library" is called a resampler, of which there exist multiple implementations.
@Tiny see https://github.com/stakira/OpenUtau/wiki/Resamplers-and-Wavtools

I wonder how easy it is to pulg that into whatever api a tts engine exposes
Resamplers and Wavtools

Open singing synthesis platform / Open source UTAU successor - stakira/OpenUtau

GitHub
@tay I mean, I'd have to learn how tts engines function for that, but it could be anywhere from changing the tts voice bank to teto or coding a new tts on my own if tts doesnt function by playing different sounds in order
@Tiny hmm, it seems like it just is a program that takes an input / output file path and flags.

I wonder how real-time this is.
@tay id assume thats based on computer speed? as it doesnt appear to generate in real time but rather creates files in sequence
@Tiny yeah, so probably not suitable for like, screen readers.
@tay shedding a tear for teto possibilities,, i must now change my reply to "replacing my tits with kasane teto"