Supertonic
Generates speech in 31 languages with a lightweight 99M-parameter ONNX model through native and OpenAI-compatible HTTP endpoints.
What it provides
Connect an HTTPS inference API. Model weights stay on CPU/GPU infrastructure and are never installed inside the 4 GB bot.
Connection requirements
Run `pip install 'supertonic[serve]'` and `supertonic serve` outside the bot, publish port 7788 through an authenticated HTTPS reverse proxy, keep Bearer selected, and paste the proxy token below. The upstream server binds to loopback by default and does not add authentication, so never expose it directly. Keep the 99M-parameter ONNX model and audio processing on the external CPU host.
- Protocol
- OpenAI-compatible REST
- Endpoint
https://supertonic.example.com- Authentication
- bearer
Where to add it
Open Dashboard Tools, select a running OpenClaw or Hermes instance, then use the card’s Install or Connect action. External services may require an HTTPS endpoint and credentials; the dashboard shows those fields before anything is saved.