Instructions to use Superclonica/superclonica with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Supertonic
How to use Superclonica/superclonica 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
App for Superclonica?
#1
by Syams - opened
Can the Superclonica model be used in all applications that support Supertonic 3, such as Pinokio and VoiceStudio?
SuperClonica isn't a separate set of weights β it's an inference engine for the same Supertonic 3 model (same voices, same seeds), just faster and cleaner. So:
- Voices: any SuperClonica voice is a standard Supertonic 3 voice-style JSON, so it works in any Supertonic 3 app that lets you load a custom voice file.
- Engine speed-ups and fixes only apply when you run speech through SuperClonica itself (
pip install/ CLI / local server). Apps like Pinokio or VoiceStudio use their own Supertonic 3 code, so they won't get those unless they integrate the engine.
Which app do you use? If there's interest, we can look at a Pinokio script for SuperClonica.