Instructions to use Supertone/supertonic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Supertonic
How to use Supertone/supertonic 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
100% on-device AI voice chat with Supertonic
Hi Supertone,
Congratulations on the release of Supertonic TTS, a really innovative product!
I have built a 100% on-device AI voice chat system using Supertonic, Silero VAD and Whisper. Mine happens to call out to a Claude LLM for the actual LLM messaging, but it could easily be swapped to use a local LLM model for 100% on-device voice chat.
I'm thinking about open sourcing this on github, but I wondered if you guys might like to offer it instead? I would be happy to share code with you.
Best regards,
Rick
Noice! Look forward to the github link.
Thank you for your interest! @RickRossTN
If you share it on your GitHub, we will include it in the “Related Projects” section of our repository’s README.md :)
Hi @anlgboy-cream - here it is...
HuggingFace demo space: https://huggingface.co/spaces/RickRossTN/ai-voice-chat
GitHub source: https://github.com/irelate-ai/voice-chat
If you have any suggestions to improve it please let me know.