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 voice clone!!!
Gods, I truely need this model, I’ve tried a bunch of similar models, especially on edge devices, and honestly none of them come close. In real edge deployment tests, this thing just runs smoother, faster, and more reliably than everything else I’ve used.
Please, please consider adding voice cloning support. I’m begging 🙏
or finetuning please !
https://github.com/Topping1/Supertonic-Voice-Mixer
I found (and used) this, its not voice cloning or fine tuning, but it allows you to mix voices from what they already have.
Hello! We've just released Voice Builder, a service that lets you create your own custom voices.
You can try out voices directly on the webpage and download your voice styles as JSON files for use in Supertonic 2.
Hope you find this useful!
Voice Builder: https://supertonic.supertone.ai/voice-builder