Kanru Hua, probably best known in the community as the developer of Moresampler for UTAU has revealed that he is developing his own singing voice synthesizer codenamed ‘Synthesizer V’
Let’s focus on what Synthesizer V can do based on the video:
- First off, we can see that the program is being demonstrated on Ubuntu. This means that it runs on Linux which is something we don’t see often as most software is either for Windows or for macOS.
- Like most singing voice synthesizers. it has a piano roll interface where you’d plot down the notes.
- Currently, the voice database includes a female voice capable of singing in English, Japanese, and Chinese and a male voice in Chinese
- The synthesis engine has settings where it can be set to a particular singing style. It only has the option for Pop and Classical for now.
Hua, a student at the University of Illinois, is working on Synthesizer V as his final project for a music programming course he is taking. He has been pursuing research in vocal synths for years already and has been involved in many projects in the past.
Since this is still in active development, several changes and improvements as well as new features are expected to be introduced in the future.