Q: Do I have to use the character's story in my songs?
A: Of course not! They are mainly just for fun.
Q: Can I profit off of my works that use QVoice?
A: Yes. As long as you follow the QVoice Usage Guidelines, Vorcatex Character Guidelines and are using the full version.
Q: Do I have to say that I used QVoice in a song? Do I have to say which character or voicebank I used in my song?
A: You do have to say that you used QVoice in your song along with the character you used the voice of. You don't have to say wich voicebank though.
Q: Will UTAU, DeepVocal or NIAONiao voicebanks work in QVoice?
A: Sadly not. QVoice voicebanks requiere much more samples to work then UTAU, DeepVocal or NIAONiao voicebanks.
Q: Can I make my own vocals for QVoice?
A: Voicebank creation will be handled like how it's handled for CeVIO or SynthV due to the user needing to own the full version of Kontakt. Studios will only have to pay once for a dev kit unless they want to try a new language. Dev kits will be relatively cheap. We're hoping to have them cost up to $300 USD depending on how many samples the kit requires. For example, Japanese will be on the cheaper side as it will require around 6,550 samples. This includes RX, BRE, start and end breaths. We are planning on holding events where you can get your voicebank imported or you can make a voicebank for QVoice. The winners of these events will have 95% control over the project.
Q: What's the differences between the lite and paid version? Is the lite version a timed trial?
A: The lite versions only contain 3 pitches and can only read .mid files. It is not a timed trial.
Q: How is it that you are using "pitch based" synthesis and also NNSVS?
A: QVoice will mainly be concatenative synthesis (ie VOCALOID). For the AI integration, we'll be taking pieces from NNSVS then adjusting that to our needs. NNSVS will essentially be used as a "sketch" for QVoice's AI and it will grab traits from samples of a voice provider singing and add them to a voicebank. This is to help vocals sound more unique.
Q: What will the phonetics be based on?
Q: Will there be dialect support?
A: Chinese will have built in support for Cantonese and Taiwanese. English will primarily support Old English, Middle English, Received Pronunciation, General American and Australian. There will be a few phonemes for Scottish English, UK English, Welsh English and Canadian. Japanese will have Amami Ōshima, Okinawan and Kansei-ben support.
Q: Why "QVoice" for the name
A: There isn't much of a reason behind the name. We just thought it sounded nice.
Q: Will there be public beta
A: Yes! One of the perks the Indiegogo will have is testing QVoice while its not stable enough to have a public beta. Once we're sure its stable enough (ie: not crashing every 5 minutes), we'll open a fully public beta. Backers will get updates early once a public beta is released as well as access to the full versions of the vocals.
Q: When are you launching the Indiegogo?
A: November or early December.
Q: When it'll be released?
A: We are hoping that the initial public beta will be released in the first half of 2022. The major release will probably be in late 2022 or 2023 if everything goes according to plan.