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
pipecat-supertonic for Supertonic TTS in pipecat
Hello everyone, I built pipecat-supertonic for using Supertonic TTS as a Pipecat TTSService. I wasn’t sure whether this should be integrated into the core project, so I released it as a separate integration for now.
Github : https://github.com/architjambhule66-debug/pipecat-supertonic
pypi : https://pypi.org/project/pipecat-supertonic/
Happy to improve the integration if you guys have any feedback.
Hi @Archit-01 ,
Thank you for building this — this is really nice to see.
A Pipecat TTSService wrapper makes a lot of sense for Supertonic, especially for local voice-agent and real-time assistant use cases. We appreciate that you released it as a separate integration first.
We’ll take a look at the package and examples. The main things we’d want to check are compatibility with the latest Supertonic Python SDK, multilingual settings, audio format / sample rate handling, warmup behavior, and how it behaves in a live Pipecat pipeline.
If everything looks good, we’d be happy to mention it as a community integration from the Supertonic side.
Thanks again for putting this together!