I want to create a VOICEROID-UTAU like VocalSynth...But I'd need help!

Seadust

Teto's Territory
Hello! I'm Seadust! I'm new here and I have a big project in mind..


I desire to create a freeware program that let's you make a Talkloid ! I have plans to add inotations like VOICEROID too and maybe a possible detailed inotation editor where you can get the exact flocculation you want. Also, possibly put resamplers and wavtools to render it differently depending on what one you chose to use. I also would want a flag-like system where you could change what emotion you would what you're talkloid to express ( this would require most likely you recording for different emotions ofc). I want this to be as diverse as UTAU, where people have made different recording lists ,resamplers, and etc. I thought this could be a different way to make Talkloids and I really wanna make this happen! But this is all just ideas and the issue is that ... I have no idea how to code or even how to make any of this happen . So, if anyone would want to help me at all with this project that would be amazing!! If you do (or don't) know code don't worry, I wouldn't make you all of the work! I plan to learn all of this as I am really passionate in this idea. So I really would appreciate any help I could get as I have never done anything like this before!!

(The name to this project is possibly TokuTalk ? Just an idea and I like the name :smile: ) (This name may or may not change in the future)

Thank you so much in advance!!
 
  • Like
Reactions: Abc2557

Abc2557

Teto's Territory
I don’t know how to help or anything but I think this idea is absolutely amazing!! I wish you best of luck on this and I really hope to see it as an actual program someday!!
 
  • Like
Reactions: Seadust

bio

VocalSynth Enthusiast
Supporter
Defender of Defoko
Sadly I dont know many people to help with this project, but my advice to you would be -- learn how to code and do extensive research on text to speech, training data, dict building, etc., etc.
It's gonna be a long process even if you have people helping you. Also a design doc / project outline would really help as well
 
Last edited:

Seadust

Teto's Territory
Thread starter
Sadly I dont know many people to help with this project, but my advice to you would be -- learn how to code and do extensive research on text to speech, training data, dict building, etc., etc.
It's gonna be a long process even if you have people helping you. Also a design doc / project outline would really help as well

Thank You so much!! I'm an absolute beginner on this could you point me anywhere at all? Also I definitely understand that I will not get this done in a day! I also looked that UTAU uses C++ but other programs I'm not so sure. So, I would probably use that!
[doublepost=1611529264][/doublepost]
I don’t know how to help or anything but I think this idea is absolutely amazing!! I wish you best of luck on this and I really hope to see it as an actual program someday!!

Thank You!! I had an Idea to make a Singing Synth possibly once this project is mostly finished. ( I've seen people who want to make custom voicebanks on Neutrino . So, after TokuTalk I'd want to make an AI singer type synthesizer . But that'll be after I'm satisfied with TokuTalk!)