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
I love Supertone
I just wanted to say thank you to the Supertone team for releasing this awesome new model. It’s amazing that we can run Supertone 2 efficiently and in real time on low compute devices like phones. This opens the door to building applications that previously weren’t possible in real time or only worked at much lower quality. The newly added languages, in particular, are a huge improvement. Love what you’re doing 💛
Thank you so much for the kind words and support. It really means a lot to the team.
We have just released Supertonic 3, which keeps the on-device / low-compute use case as a core goal while expanding language support to 31 languages and improving reading stability, especially around repeated or skipped words.
You can try the new release 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
We’d love for you to give Supertonic 3 a try. Thanks again for the encouragement!