Search results

Well, Taiwanese Mandarin and Mandarin from mainland China are fairly different. For example, retroflexes are typically changed to postalveolar consonants. Another example is that [f] may become more similar to [h] and the nasal endings of -n and -ng might merge, making [zheng] and [zhen] into...

Well, majority of her UTAU voicebank's tone was due to the program itself. Listening to her raw recordings and comparing them to the AI vb (especially solid or sweet), you can definitely hear the voice provider's natural sound correlation. This was always going to be an issue; sample-based...

I heavily disagree regarding Sweet. I think the difference is fairly audible. Sweet and Solid are my favorite, I think they sound most like her UTAU voicebank. Overall, very pleased with her vocal; I think she sounds great and will be very versatile

First demo is out!

They said she would be releasing in the new year, not necessarily on New Years. They tweeted a happy new year tweet and that development is coming smoothly, as well as to expect something soon.

The English version of the interface is out

| Vocaloid | -> V6 will revive new companies to produce voicebanks -> Gackpo will receive an AI voicebank for V6 -> Vsinger will announce their official departure from the engine -> The contest Vocaloid will have a positive reception | CeVIO AI + VoiSona | -> Ci Flower will surpass expectations...

Still not impressed or amused with the latest stream of SV releases and the "rock vocals" that DT is making don't really feel rock at all. It could be bad demonstrations...but how can they not come up with good demo songs?

This is so gorgeous....I really wish he just did all of them

My problem with these non-company produced demos is that you can tell the tuners don't know how to use the program most the time T_T

The technology that took hours to render was what they featured in a 2018-19 post before CeVIO AI's debut, the introduction of DNN rather than HMM. CeVIO AI and VoiSona both use the presented DNN, but it's a much weaker system to compensate render speeds. VoiSona's vocoder(s) are [excluding...

VoiSona isn't cloud based, only subscription based. Yes, you can subscribe from anywhere.

Absolutely love them; THIS is what I want. High quality vocals with enamoring concepts

Check the Emvoice One thread on Utaforum

The letters are very boring, and there's so many they're just becoming too much; there's only so many colors and the initial schemes are running out as well. Additionally, they look...like they were thrown together in clip studio as fast as possible with the terrible cropping. I really would...

They, to my knowledge, are not developers or owners. They simply are taking over the licenses for advertising purposes, so we are still likely not going to receive any updated products :(

I'm fairly certain they're trained on a mix of the original samples, untuned renders from SV Basic, and other filler data.

I've seen people compare the audio output and their reasoning is "it's free and open source". Those are two different comparisons...

This is true, but there's no way to add growl samples to V2 banks. HOWEVER, if you cross-synth a V4 and V2 vb with the V4 vb being the base, you can use growl.

I'm getting really tired of people saying SynthV, CeVIO, and V6 are worse than NNSVS; even just comparing them is frustrating to see. NNSVS is cool and fun, I love it being an open source alternative for fan creations...but saying it's better in any form than commercial products that receive...