Platform edition

Supertonic (Experimental) for Windows

Local Supertonic 3 text-to-speech with 10 voices and 31 languages, generated on your CPU with ONNX Runtime after a one-time model download.

Version: 1.2.2
Plugin ID: com.typewhisper.supertonic-tts
Requirements: TypeWhisper 1.1.0 or newer · Windows 10 or newer · About 383 MB of disk space and an internet connection for the one-time model download

Inside this edition

Speech generated on this device, without sending text to a cloud service
10 preset voices (M1 to M5, F1 to F5) and 31 languages
CPU synthesis with ONNX Runtime and playback through Windows audio
Model download from Hugging Face, checked by size and SHA-256, only after you accept the OpenRAIL-M license
Speech speed from 0.9 to 1.5 and quality from 1 to 16 denoising steps
Load and unload the model without downloading it again

Select Read model license, then tick I have read and accept the model license terms
Optionally enter a Hugging Face token and select Save token; public downloads work without one
Select Download & Load to download the model and start it
Set Speech speed and Quality, then select Save settings

Set up the add-on and verify its platform-specific capabilities with a first practical workflow.

Roles in TypeWhisper

Text-to-Speech

In TypeWhisper, open Settings > Discover plugins and install Supertonic (Experimental), which is listed there as Supertonic TTS. The add-on then appears in the Settings sidebar, and its page opens. If it is already installed, open its page in the sidebar.
On the add-on's page, review the options available in this edition.
Select Read model license, then tick I have read and accept the model license terms
Optionally enter a Hugging Face token and select Save token; public downloads work without one
Select Download & Load to download the model and start it
Set Speech speed and Quality, then select Save settings
Under Settings > Advanced > Spoken feedback, turn on Spoken feedback and choose a voice from Supertonic TTS under Voice.

Text-to-Speech: Enable spoken feedback, select Supertonic TTS as the voice provider, and test a short sentence before adjusting speed or quality.