Supertone AI is an expressive text-to-audio platform that brings back Freddie Mercury’s voice


Supertone AI is an expressive text-to-audio platform that claims to take on the publishing industry.

Beyond text-to-speech

Supertone’s technology represents a leap forward in traditional text-to-speech synthesis. The company has developed a proprietary speech synthesis technology called Nuvo.

This not only speaks and sings, but also captures emotions. This technology enables the production of voices that are virtually indistinguishable from human voices.

Supertone’s Controllable Voice Conversion (CVC) technology allows users to convert their voice into any other voice in real-time. This means that users can transform their voice into that of a man, an old person, a woman, or even a child, playing multiple characters as needed.


It’s not just voice cloning like Eleven Labs or Descript, it’s voice augmentation.

This makes the text-to-speech platform perfect for audiobooks, where different voice types are needed for different characters.

Recent results include this performance of the voice of a deceased South Korean pop star.

Or this performance of Freddie Mercury in Korean.

Customizing Voices

Supertone Nuvo also gives users the option to customize their voices. There are pre-selected base voices that users can select and design for further customization. This technology uses neural networks trained on unsorted data of the target voice to produce raw audio, providing a natural voice synthesis process.


Leave a Comment

Your email address will not be published. Required fields are marked *

Scroll to Top