Phoonnx Glowtts
per-voice-see-provenance-table
Model source
- Kind
- Other
- File size
- 109–110 MB
- Version
- vRevision df84529
- Updated
- Sep 19, 2026
- Downloads
- 0
- Tasks
- Audio
- Source
- Hugging Face
Source description
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.
Sources
1 source
Sources
1 sourceVerified Sep 19
Model artifacts
58 artifacts
Model artifacts
58 artifactscoqui-be-common-voice-glow-tts/model.onnx
onnx · 109 MB · SHA-256 8740516ee17c…a6d8 · Hugging Face
Downloadcoqui-en-ljspeech-glow-tts/model.onnx
onnx · 110 MB · SHA-256 28d3c98a079f…d656 · Hugging Face
Downloadcoqui-it-mai_female-glow-tts/model.onnx
onnx · 109 MB · SHA-256 a77a1ed2d677…c81d · Hugging Face
Downloadcoqui-it-mai_male-glow-tts/model.onnx
onnx · 109 MB · SHA-256 7e92dde327b1…2848 · Hugging Face
Downloadcoqui-tr-common-voice-glow-tts/model.onnx
onnx · 109 MB · SHA-256 0b8b655c9294…bff3 · Hugging Face
Downloadde-de-rebecca_braunert_plunkett/model.onnx
onnx · 109 MB · SHA-256 d7712f90ef11…9c15 · Hugging Face
Downloaden-us-northern_english_male/model.onnx
onnx · 109 MB · SHA-256 d32185ba5cf6…54e1 · Hugging Face
Downloaden-us-scottish_english_male/model.onnx
onnx · 109 MB · SHA-256 df22ee7e9f8e…da1a · Hugging Face
Downloaden-us-southern_english_female/model.onnx
onnx · 109 MB · SHA-256 545c26ee6209…6ac4 · Hugging Face
Downloaden-us-southern_english_male/model.onnx
onnx · 109 MB · SHA-256 0426dc97ab71…5cef · Hugging Face
DownloadSource excerpts
2 excerpts
Source excerpts
2 excerpts--- license: other pipeline_tag: text-to-speech library_name: phoonnx tags: [phoonnx, glowtts, larynx, tts] --- # phoonnx-glowtts GlowTTS voices for [phoonnx](https://github.com/TigreGotico/phoonnx) — flow-based acoustic models (text → mel), paired with a vocoder from [phoonnx-vocoders](https://huggingface.co/OpenVoiceOS/phoonnx-vocoders). One voice per subfolder (`model.onnx` + native `config.json`). **58 voices**, 15 languages. Part of the [phoonnx community mirror](https://huggingface.co/collections/OpenVoiceOS/phoonnx-community-mirror-6a2204d302e0e7497870cd68). | source | count | tokenization | vocoder | |---|---|---|---| | [Larynx](https://github.com/rhasspy/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 ```python 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](https://github.com/TigreGotico/phoonnx/blob/dev/docs/glowtts.md).
Source context: 0 downloads · 0 likes · Pipeline text-to-speech · Library phoonnx · Repo OpenVoiceOS/phoonnx-glowtts
