Downloads · 30 days
0
phoonnx-optispeech
OpenVoiceOS/phoonnx-optispeech
phoonnx-optispeech 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 mit.
OptiSpeech voices for phoonnx — non-autoregressive (FastSpeech2-style) acoustic + GAN vocoder, single ONNX (waveform out). One voice per subfolder (model.onnx + native config.json). Mirror of mush42/optispeech, en-US,…
Access
Public
Updated Sep 10, 2026
Repo size
228 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx228 MB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- phoonnx
- License
- mit
- Access
- Public
- Created
- Jun 5, 2026
- Updated
- Sep 10, 2026
- SHA
- cf254d4c
Model card
From the Hugging Face model README
phoonnx-optispeech
OptiSpeech voices for phoonnx — non-autoregressive (FastSpeech2-style)
acoustic + GAN vocoder, single ONNX (waveform out). One voice per subfolder
(model.onnx + native config.json). Mirror of
mush42/optispeech, en-US, 24 kHz.
Part of the phoonnx community mirror.
| voice | acoustic | speaker |
|---|---|---|
mush42__optispeech-lightspeech-en-us-emily | LightSpeech | emily |
mush42__optispeech-lightspeech-en-us-mike | LightSpeech | mike |
mush42__optispeech-convnext-en-us-emily | ConvNeXt-TTS | emily |
The native config.json is generated from OptiSpeech's embedded ONNX metadata.
See docs/optispeech.md.
- Task
- Text-to-Speech
- Library
- phoonnx
- License
- mit
- Created
- Jun 5, 2026
- Updated
- Sep 10, 2026