whatmodel.sh / tts / Supertonic 3

Supertonic 3

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Supertonic 3 is an open-weights text-to-speech model from Supertone, released May 2026. Its published size is 0.099B parameters. Licence: openrail-m.

Catalogue identity notes

Supertone/supertonic-3 (on-device ONNX TTS, 31 languages, 'about 99M parameters across the public ONNX assets' per card). Model OpenRAIL-M; sample code MIT.

55.0±9.7#52 of 118 text-to-speech modelsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

Score within the Vapi Humanness · Bradley–Terry rating, 2026-09-25 snapshot comparison set only.

$ how it compares

The text-to-speech models ranked either side of Supertonic 3, out of 148 with a score.

#modelscorewhereRAMreleased
62Deepgram Aura 2 Deepgram57±3api $30.00/M chars2025-04
63ZONOS2 8B Zyphra57±2local~5.2GB2026-06
64Supertonic 3 Supertone55±10local~0.4GB2026-05
65ElevenLabs v3 Alpha ElevenLabs55±9comparison only2025-06
66Higgs Audio V2 Boson AI55±3local~7GB2025-07

see all text-to-speech models · find the ones that fit your machine

$ what it's good at

other tests1 not in a task · 62% of its score
testresultvs the others in its rundifficultycountswhy
Arabic TTS Arena · community blind A/B rating, 2026-09-24 snapshot1051.4 ✎▂▂··▃·█▅···▂ beats 7/12avg 1018▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 62%blunt

$ where to run it

Other ways to run it

version

  1. Run it as published · needs ~0.4 GB · from github.com/supertone-oss-archive
    pip install supertonic && supertonic tts 'Supertonic is a lightning fast, on-device TTS system.' -o output.wav --lang en

Official weights and documentation: huggingface.co/Supertone ↗

$ how the score was worked out · Arabic TTS Arena (Navid AI) ·… 62%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-241▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 62%Apache-2.0
prior · pull toward the middle▇▇▇▇▇▇▇▇▇▇▇ 38%
weighted average= 55.0

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json