whatmodel.sh / tts / Vokan
Vokan
↗ share
+ contribute
Vokan is an open-weights text-to-speech model from ShoukanLabs, released March 2024. Licence: mit.
Catalogue identity notes
ShoukanLabs/Vokan, a StyleTTS 2 fine-tune.
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 Vokan, out of 148 with a score.
| # | model | score | where |
|---|---|---|---|
| 89 |  SILMA TTS v1 | 48±10 | local |
| 90 |  FireRedTTS (v1) | 48±3 | local |
| 91 | Vokan | 48±14 | comparison only |
| 92 |  Orpheus TTS 3B 0.1 (finetune-prod) | 47±5 | api $15.00/M chars +local |
| 93 |  Kyutai TTS 1.6B en/fr | 47±5 | local |
see all text-to-speech models · find the ones that fit your machine
$ what it's good at
other tests1 not in a task · 17% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| TTSDS v1 · default four-factor score | 84.5% ✎ | ▂▂····▃·▃▅▂█ beats 5/14 | 17% |
$ where to run it
No verified API or download recorded yet · add one
Official weights and documentation: huggingface.co/ShoukanLabs ↗
$ how the score was worked out · TTSDS v1 published results 17%
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
| source | results | share of the score |
|---|---|---|
 TTSDS v1 published results | 1 | 17% |
| prior · pull toward the middle | 83% | |
| weighted average | = 47.6 |
$ improve this page
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