Supertone

/

supertonic

like 478

Follow

Supertone 389

Hello! The current open-weight model supports English only. While we may consider additional languages in the future, there is no specific plan at this time.

The Korean language works with v2, but you have to manually load the model and use the example with the helper module. Now I'm waiting for the pip package to be updated to make installation easier for users.

https://github.com/mitrokun/wyoming_supertonic

Thanks for the question, and sorry for the delayed update.

Korean is supported in Supertonic 3 (and 2). The updated release expands language support to 31 languages, including Korean (ko), and the Python package can now download and use the updated model automatically.

You can install it with:

pip install supertonic

Example:

from supertonic import TTS

tts = TTS(auto_download=True)
style = tts.get_voice_style("M1")

wav, duration = tts.synthesize(
    "회의는 곧 시작되고 모두 조용히 자리에 앉아 듣고 있습니다.",
    voice_style=style,
    lang="ko",
)

tts.save_audio(wav, "korean.wav")

You can also try the updated 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