When to choose Supertonic
Consider the curated Supertonic package for English speech. For another language, check a compatible Qwen3-TTS CustomVoice conversion instead.
- Outmake package
- Supertonic 3, int8, 11 May 2026
- Download
- 129 MB
- Speakers offered in Outmake
- 8
- Language requested by Outmake
- English
- Model licence
- OpenRAIL-M
Where shown, download sizes are rounded from the app’s pinned packages. They exclude the shared speech engine and do not measure runtime memory.
Check the version as well as the name
Outmake’s curated entry points to a dated Supertonic 3 package from sherpa-onnx. The app offers eight numbered speakers for that package.
The upstream model is multilingual. Outmake’s curated command-line runtime, however, explicitly requests English. A multilingual model card does not make the app’s current synthesis path multilingual. Use this curated package for English.
Two controls affect the reading
Outmake exposes speed and generation steps for the curated Supertonic voice. Speed changes the pace. Steps affect the generation process and can change how long it takes to produce speech.
Change one control at a time while playing the same sentence. This makes it possible to hear the effect without mistaking a different passage for an improvement.
OpenRAIL-M includes use restrictions
Supertonic’s model licence lists uses that are prohibited. Read it before using generated speech commercially or distributing a product built around the model.
Local generation describes where the audio is made. It does not remove the model’s licence terms or give permission to impersonate someone.
Run Supertonic in Outmake
Outmake is free and requires macOS 26 or later on Apple silicon. These voice models run locally after their files have downloaded. You can also follow the upstream project links below to use another runtime.
- Open Models, then Voices.
- Open Supertonic. Check the licence shown on its card.
- Choose Get. Once downloaded, play a sentence in the voice’s page.
- Choose Use to make it the local voice. To hear a reply, open its menu and choose Read Aloud.
Voice settings and read-aloud help explain how to choose voices and stop playback. This page is about generating speech. For speech-to-text, use dictation or transcription instead.
Before you rely on it
- Eight is the number of distinct speakers offered by Outmake, not a claim about the maximum supported upstream.
- The curated runtime requests English. No non-English app support or speed benchmark is claimed here.
Try a short passage before committing to a long one. Local speech keeps synthesis on your Mac; it does not make an online chat model local. Outmake’s privacy policy explains the difference.
Sources
Model cards and runtime documentation checked 11 November 2026. App-specific details were checked against Outmake’s voice catalog and runtime configuration. No new listening test or speed benchmark was performed for this guide.