whatmodel.sh / tts / Glow-TTS Common Voice (Turkish)
Glow-TTS Common Voice (Turkish)
↗ share
+ contribute
Glow-TTS Common Voice (Turkish) is an open-weights text-to-speech model from Coqui TTS / Fatih Akademi, released March 2022. Licence: MIT.
Catalogue identity notes
Exact registry entry tts_models/tr/common-voice/glow-tts. Default vocoder vocoder_models/tr/common-voice/hifigan. Model archive responded HTTP 200 to a HEAD request on 2026-09-29. CPU command documented by maintained Coqui TTS; phoneme models may require the espeak-ng system package. Memory is an estimated 4GB runtime budget, not measured usage. No original-paper MOS transferred to this separately trained checkpoint.
Model information sources
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 Common Voice (Turkish), out of 148 with a score.
| # | model | score | where |
|---|---|---|---|
| 144 |  MMS TTS Turkish | 18±4 | local |
| 145 |  Antalia 1 | 17±3 | comparison only |
| 146 |  Amphion NaturalSpeech 2 (LibriTTS) | 14±3 | local |
| 147 | Glow-TTS Common Voice (Turkish) | 11±4 | local |
| 148 |  FreyaTTS-small | 9±4 | 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 · 94% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Freya-TR-Eval Turkish TTS intelligibility (WER, faster-whisper large-v3, 8 kHz band) | 10.9% ✎ | ▄··▄··▄···▂█ beats 1/10 | 94% |
$ where to run it
Other ways to run it
- Run it as published · needs ~4 GB · from github.com/idiap
uv run --python 3.11 --with 'coqui-tts[languages]' --with torch --with torchaudio --with torchcodec tts --model_name tts_models/tr/common-voice/glow-tts --text "Merhaba dünya." --out_path speech.wav --device cpu
Weights and documentation: github.com/idiap ↗
$ how the score was worked out · Antalia-2 Mini model card (cl… 94%
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 |
|---|---|---|
 Antalia-2 Mini model card (cloud0day3/antalia-mini), public Freya-TR-Eval re-run table | 1 | 94% |
| prior · pull toward the middle | 6% | |
| weighted average | = 10.5 |
$ 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