In this week’s podcast episode, I sit down with the brilliant Kanru Hua, the founder of the music software company Dreamtonics which created the Synthesizer V and Synthesizer V Studio voice synthesis applications.
A cumulation of years of AI research, signal processing, and musical passion led to Synthesizer V, which faithfully replicates the nuances of the human singing voice.
Its voices are available natively in English, Japanese, and Chinese, and the software even allows any voice to sing in any of those three languages.
Pretty fascinating, right?
In this episode, Kanru and I discuss the many legitimate uses for vocal cloning, the evolution of Synthesizer V, how to use cloned vocals as guides for human singers, the challenges of vocal synthesis, and so much more.
You can automatically access the podcast from your favorite podcast provider just by clicking on this link, or you can go to bobbyoinnercircle.com like always.
Also, a video version is now available on YouTube as well.
