A new Vocal Synthesis plugin (VST/AU) called Emvoice One has just been released. Featuring a pitch and lyric editor it can provide realistic (at least better than we've heard before) singing vocal melodies. You can also type the lyrics in to match each note so it will sing what you ask.
It uses deeply sampled vocals rather than synthesis or physical modeling, which is perhaps why it has a different character than other physical modeling approaches. As with any vocal, its all in the imperfections, Lucy still sounds as if she's been heavily autotuned, but its certainly an improvement. It reminds us a little of Dubstar vocalist Sarah Blackwood.
The first voice, Lucy has been released with the plug-in more voices presumably to come.
The demo video is OK but we think this one seems to give more of s sense of what it can do:
Emvoice takes a different approach. We’ve broken sung vocals down
to the granular level, recording the elements that make up individual phonemes at multiple pitches. Thousands of samples are reconstructed by a sophisticated cloud-based engine that returns the completevocal to your system over the internet, at lightning-fast speed. What you’re hearing when you listen to Emvoice One isn’t artificial – it’s a real singer’s voice, recombined to interpret your own words.
Available now priced at $199, although you can access a free version which has limited range of notes until a full voice is purchased.
More information: https://emvoiceapp.com/
With Kavus Torabi and Michael J. York
Three new compact creation tools
Self assembly too
New desktop from Moog