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
Built a desktop TTS studio GUI for Supertonic 3 - VoxCraft
Hey Supertonic team - love the v3 release. The 31-language support and expression tags are incredible.
I built a desktop studio around it to make it more accessible: https://github.com/ShyamKumar1/voxcraft
It's a FastAPI backend + vanilla JS single-page frontend. Features:
-- Visual voice selection (10 presets with descriptions)
-- Speed slider, quality slider, language dropdown
-- WaveSurfer.js waveform preview with play/pause
-- Batch mode for multiple texts
-- Generation history with search
-- Keyboard shortcuts (Cmd+Enter to generate, Space to play)
Everything is local, MIT licensed. Would love feedback from the Supertonic community β especially on voice quality tuning and any quirks I should know about with the ONNX runtime.