Instructions to use Supertone/supertonic-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Supertonic
How to use Supertone/supertonic-2 with Supertonic:
from supertonic import TTS tts = TTS(auto_download=True) style = tts.get_voice_style(voice_name="M1") text = "The train delay was announced at 4:45 PM on Wed, Apr 3, 2024 due to track maintenance." wav, duration = tts.synthesize(text, voice_style=style) tts.save_audio(wav, "output.wav")
- Notebooks
- Google Colab
- Kaggle
Please add Russian
It would be great if you could add Russian and the ability to create your own styles!
Hello! Thank you for the suggestion. We hope to expand language support in future versions. Also, we will introduce a service that allows users to create their own voice styles in the near future.
We appreciate your feedback and interest 🙂
Жду не дождусь !!! самая лучшая TTS
Thanks again for the suggestion and for the kind words!
Russian is now supported in Supertonic 3. The new release expands language support from 5 languages to 31 languages, including Russian (ru), while keeping on-device inference as a core use case.
You can try it here:
- Hugging Face demo: https://huggingface.co/spaces/Supertone/supertonic-3
- Model: https://huggingface.co/Supertone/supertonic-3
- GitHub: https://github.com/supertone-inc/supertonic
Creating custom voice styles is not included in the current open-weight release, which provides a fixed set of voices. However, zero-shot voice cloning and more flexible voice style creation will be available through the upcoming Supertone Play and API services. We’ll share more updates when they are ready.
Thank you again for the feedback and support!