Back to Catalog

Supertonic-3

Model

Supertonic TTS 3 is an open text-to-speech model developed by Supertone. The model is based on an architecture utilizing flow matching and is designed with an emphasis on efficient speech synthesis under low computational demands. It supports 31 languages, including Slovak, and enables speech generation from text input as well as zero-shot voice cloning from a short reference recording.

Contributors
Supertone
License
MIT License
Language
sk, eng, other
Modality
Speech/audio
Task
Text-to-speech