whatmodel.sh / tts / Glow-TTS + HiFi-GAN (VCTK, VITS study)
Glow-TTS + HiFi-GAN (VCTK, VITS study)
↗ share
+ contribute
Glow-TTS + HiFi-GAN (VCTK, VITS study) is a closed-weights text-to-speech model from VITS study (public implementations), released June 2021.
Catalogue identity notes
Comparison-only. Exact VCTK multi-speaker system in VITS (ICML 2021) Table 3 row 'Glow-TTS + HiFi-GAN': jaywalnut310/glow-tts with global speaker conditioning, trained on VCTK by the VITS authors (§4.2), HiFi-GAN second stage without fine-tuning. Study-specific weights, not released; distinct from glow-tts-hifigan-ljspeech and coqui-en-ljspeech-glow-tts.
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 Glow-TTS + HiFi-GAN (VCTK, VITS study), out of 148 with a score, then more from VITS study (public implementations).
| # | model | score | where | ||
|---|---|---|---|---|---|
| 133 |  Parler-TTS Large v1 | 29±3 | local | ||
| 134 |  WhisperSpeech v1.95 Medium (7-language) | 28±3 | local | ||
| 135 | Glow-TTS + HiFi-GAN (VCTK, VITS study) | 28±6 | comparison only | ||
| 136 |  HierSpeech++ (LibriTTS-960) | 28±5 | local | ||
| 137 |  Piper (tr_TR dfki medium) | 26±4 | local | ||
| more from VITS study (public implementations) | |||||
| 142 | Tacotron 2 + HiFi-GAN (VCTK, VITS study) | 19±6 | comparison only | ||
see all text-to-speech models · find the ones that fit your machine
$ what it's good at
other tests1 not in a task · 87% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| VITS 2021 VCTK human MOS | 3.76 / 5 ✎ | █····█·····█ beats 1/2 | 87% |
$ where to run it
No verified API or download recorded yet · add one
Weights and documentation: github.com/jaywalnut310 ↗
$ how the score was worked out · VITS: ICML 2021 original list… 87%
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 |
|---|---|---|
 VITS: ICML 2021 original listening studies | 1 | 87% |
| prior · pull toward the middle | 13% | |
| weighted average | = 27.8 |
$ 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