Platform editions
Supertonic (Experimental)
Experimental local text-to-speech with Supertonic 3 ONNX models. Requires accepting the OpenRAIL-M model license before downloading model assets.
Choose your platform
This add-on has separate macOS and Windows editions. Each page documents the features, settings, requirements, and screenshots for that platform.
macOS
v1.0.1
Experimental local text-to-speech with Supertonic 3 models.
- Local text-to-speech output
- Processing without uploading audio or text
- Model or runtime downloads managed by TypeWhisper
- Explicit acceptance of the OpenRAIL-M model license
Windows
v1.2.2
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.
- 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
