Barcelona-based Voctro Labs, the company which made Spanish Vocaloids Bruno, Clara, and MAIKA, recently announced that they have worked on a new voice synthesis toolkit dubbed as Voiceful.
According to the official website, Voiceful “uses voice to create new ways of expressing yourself”. In other words, this new product is not only limited to singing voice synthesis but also includes speech synthesis from a selection of pre-made voice libraries or you can even request a custom voice model.
One interesting feature to note that it can create new speech based on existing voice recordings which are similar to Adobe Voco and Google DeepMind’s WaveNet which has previously raised concerns by experts on the potential abuse of the technology where it can generate voice statements which where not actually said by the person.
Aside from synthesis, the toolkit can also manipulate voices to create various effects and can perform voice alignment and auto-tuning.
We are just scratching the surface of what this toolkit can do for those who work in the media or advertising, software and game development, and for gadget and toy makers, among other applications. You can learn more and try a demo by checking out Voiceful.io