Instructions to use Supertone/supertonic-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Supertonic
How to use Supertone/supertonic-3 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
更多语言支持
是否有关于中文的支持计划呢?
Hi @androidli ,
Thanks for asking.
Chinese support is definitely important, and we understand why many users are asking for it.
We do have access to public / license-clean Chinese speech data, and we have internally trained versions that included Chinese. However, in our experiments, Chinese reading accuracy and overall speech quality were not stable enough for the Supertonic 3 public release, so we decided not to include it this time.
Our current guess is that Chinese is more challenging for this model family because of the much larger character / vocabulary coverage and the complexity of text-to-speech mapping, but we need more analysis before saying that with confidence.
That said, we’ve received many requests for Chinese support since the Supertonic 3 launch, and we agree that it is a very important language. We’ll keep working on it and will try to include Chinese in a future release once the quality is stable enough.
Thanks again for the feedback.