Instructions to use OpenVoiceOS/phoonnx-vits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Piper
How to use OpenVoiceOS/phoonnx-vits with Piper:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
phoonnx-vits
Per-architecture mono-repo of VITS voices for phoonnx. One model per subfolder. Part of the phoonnx community mirror.
en_US-lessac-medium,en_GB-alba-medium,de_DE-thorsten-medium,fr_FR-siwis-mediumโ Piper voices (espeak), mirror ofrhasspy/piper-voices(mit).mms-eng,mms-spa,mms-fra,mms-deuโ Meta MMS-TTS (graphemes), ONNX fromwillwade/mms-tts-multilingual-models-onnx, tokenizer fromfacebook/mms-tts-*(cc-by-nc-4.0).uk_UA-tetiana-high,uk_UA-mykyta-high,uk_UA-oleksa-highโ Piper voices (espeak), mirror ofRomanStasyshyn/uk_UA-{tetiana,mykyta,oleksa}-highby RomanStasyshyn (apache-2.0), shared via OHF-Voice/piper1-gpl#212.tw-kasanoma,ny-kasanoma,vmw-kasanomaโ Piper voices for Twi, Chichewa and Makhuwa (espeak with thelfnfront end), mirror of themichsethowusu/kasanomaGitHub releases. The source states no licence, so these carrylicense: other; read the folder README before you use them.
Licenses follow the originals per subfolder.