Search results

All vocalsynths are vocaloids.

I don't want to down on them but I hope they improve synthesis it sounds very lifeless and robotic but that might be their goal. Especially for having the synthesis be based one to one from the source data. At least the voice providers sound nice I hope they have a decent recording set up...

I think realsinger is great I wish they made a sequel to the software with higher quality synthesis it was a great concept definitely better than some of the earlier attempts like cantor.

The new update allows for phoneme editing using ARPABET similar to synth v hopefully this will help with pronunciation errors. Working on improving the pitch and timing transfer.

I main nolle to the point where I made a tts of her voice and I'm around ar50. My current team is nolle albedo fishel xanling

My first time with vocaloid was lens cover of Pon Pon Pon at the time the original wasn't on YouTube and my friend recommended it to me. I then saw mmd dances of happy synthesiser and thought it was a dance game like just dance or something.

I do think vocaloid has a problem with it's English phonetic system and it only gets worse with non native English voice banks. I don't think it's crazy to want a clear understandable voices from a hundred dollar commercial product. I'm glad new synths seem to fix this problem with better...

Updated the tts.

Retraining her for the new tts method. Fingers cross she comes out well. Will use her for some vocal Synth news and tutorials.

You could I guess still would recommend the sample pack

No reaction noises that aren't real words or laughs. Is there a reason why you would want that? Also japanese voices are still only in japanese.

Weird to have one deeper than ia but is doesn't sound bad in my opinion just like ia rocks. I could see them doing it so it does steal Lia voice but her vocaloid still exists. It is a weird choice.

New update test I'm happy to announce pitch and timing transfer. He still has some glitches I left it in so you get a true feel for the update.

Should I get them and try to make them into TTS?

So I've been thinking about what to do next I don't know what people would want. Please respond below with any questions or insight.

I think this comes down to Japan's age of consent of 13 so to them they don't see it as underage. This is a very big problem in Japan and they have been pushes to raise it to 16 and they have local laws to stop under 18 prostitution and pressured sex. Still a very questionable decision from a...

Thought it might be good to post more here Luka ai tts is in development and has 5 banks 2 mature and 3 high. They use a small amount of data like less than 10 minutes so I might combine them to get higher quality. If she is susscesful I will work on rin. I know where I can find samples for her...

If anyone wants to use the cul tts message me. I'm working on a way to have larger language support and better English.

I thought it might be good to compare it to the old cevio ai prototype

I'm honestly impressed it's not neutrino but it's better than nnsvs which is nice to have. Yes it can get pitchy but you can fix it in pitch correction software like most non commercial ai synths.