Downloads · 30 days
0
phoonnx-glowtts
OpenVoiceOS/phoonnx-glowtts
phoonnx-glowtts is a text-to-speech model from OpenVoiceOS. Use it when you need text read aloud. It is set up for phoonnx. The card lists the license as other.
GlowTTS voices for phoonnx — flow-based acoustic models (text → mel), paired with a vocoder from phoonnx-vocoders. One voice per subfolder (model.onnx + native config.json). 58 voices, 15 languages. Part of the phoonn…
Access
Public
Updated Sep 10, 2026
Repo size
6.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx6.6 GB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- phoonnx
- License
- other
- Access
- Public
- Created
- Jun 5, 2026
- Updated
- Sep 10, 2026
- SHA
- b796c880
Model card
From the Hugging Face model README
phoonnx-glowtts
GlowTTS voices for phoonnx — flow-based acoustic models (text → mel),
paired with a vocoder from phoonnx-vocoders.
One voice per subfolder (model.onnx + native config.json). 58 voices, 15 languages.
Part of the phoonnx community mirror.
| source | count | tokenization | vocoder |
|---|---|---|---|
| Larynx (MIT) | 51 | gruut IPA | HiFi-GAN |
| coqui-ai/TTS official zoo | 7 | graphemes / espeak | HiFi-GAN · multiband-MelGAN · Griffin-Lim |
Vocoders across the set: 53 HiFi-GAN · 2 multiband-MelGAN (neural, stats-normalized) · 3 Griffin-Lim.
Use
from phoonnx.model_manager import TTSModelManager
m = TTSModelManager(); m.merge_default_voices()
voice = m.voices["larynx/en-us-ljspeech-glow_tts"].load() # downloads model + linked vocoder
for chunk in voice.synthesize("Hello from GlowTTS."): ...
Acoustic models are converted to ONNX by a standalone exporter (no coqui-tts / Larynx package dependency). See docs/glowtts.md.
- Task
- Text-to-Speech
- Library
- phoonnx
- License
- other
- Created
- Jun 5, 2026
- Updated
- Sep 10, 2026