The Dii and Miro text-to-speech voices. Every voice is a VITS model in ONNX format.
AI & ML interests
None defined yet.
Recent Activity
Training sets where every recording is synthetic speech from a text-to-speech voice.
Matcha-TTS acoustic models in ONNX for phoonnx.
Supertone SuperTonic models in ONNX for phoonnx.
k2-fsa OmniVoice in ONNX for phoonnx.
Qwen3-TTS models in ONNX for phoonnx.
Orpheus models in ONNX for phoonnx.
NeuTTS models in ONNX for phoonnx.
Magpie TTS models in ONNX for phoonnx.
AI4Bharat Indic Parler-TTS in ONNX for phoonnx.
VITS voices in ONNX for phoonnx: Piper, MMS, Coqui VITS and VITS2, one voice per repo.
Kyutai Pocket TTS models in ONNX for phoonnx.
MixerTTS acoustic models in ONNX for phoonnx.
FastPitch acoustic models in ONNX for phoonnx.
Chatterbox models in ONNX for phoonnx.
Training sets made from real recordings, converted to the target voice by voice conversion.
Vocoders in ONNX for the phoonnx voices that make a spectrogram.
Rapido TTS models in ONNX for phoonnx.
Spark-TTS models in ONNX for phoonnx.
Shami (HamsVITS) in ONNX for phoonnx: Levantine Arabic and English code-switching.
OuteTTS models in ONNX for phoonnx.
YourTTS in ONNX for phoonnx: multilingual VITS that clones a voice from a speaker vector.
MOSS-TTS Nano and its audio tokenizer in ONNX for phoonnx.
Llasa models in ONNX for phoonnx.
ArkTTS models in ONNX for phoonnx: Audio8 and Zortzi.
StyleTTS2 models in ONNX for phoonnx, Kitten TTS included.
OptiSpeech models in ONNX for phoonnx.
Glow-TTS acoustic models in ONNX for phoonnx.
F5-TTS models in ONNX for phoonnx.
The Dii and Miro text-to-speech voices. Every voice is a VITS model in ONNX format.
Training sets made from real recordings, converted to the target voice by voice conversion.
Training sets where every recording is synthetic speech from a text-to-speech voice.
Vocoders in ONNX for the phoonnx voices that make a spectrogram.
Matcha-TTS acoustic models in ONNX for phoonnx.
Rapido TTS models in ONNX for phoonnx.
Supertone SuperTonic models in ONNX for phoonnx.
Spark-TTS models in ONNX for phoonnx.
k2-fsa OmniVoice in ONNX for phoonnx.
Shami (HamsVITS) in ONNX for phoonnx: Levantine Arabic and English code-switching.
Qwen3-TTS models in ONNX for phoonnx.
OuteTTS models in ONNX for phoonnx.
Orpheus models in ONNX for phoonnx.
YourTTS in ONNX for phoonnx: multilingual VITS that clones a voice from a speaker vector.
NeuTTS models in ONNX for phoonnx.
MOSS-TTS Nano and its audio tokenizer in ONNX for phoonnx.
Magpie TTS models in ONNX for phoonnx.
Llasa models in ONNX for phoonnx.
AI4Bharat Indic Parler-TTS in ONNX for phoonnx.
ArkTTS models in ONNX for phoonnx: Audio8 and Zortzi.
VITS voices in ONNX for phoonnx: Piper, MMS, Coqui VITS and VITS2, one voice per repo.
StyleTTS2 models in ONNX for phoonnx, Kitten TTS included.
Kyutai Pocket TTS models in ONNX for phoonnx.
OptiSpeech models in ONNX for phoonnx.
MixerTTS acoustic models in ONNX for phoonnx.
Glow-TTS acoustic models in ONNX for phoonnx.
FastPitch acoustic models in ONNX for phoonnx.
F5-TTS models in ONNX for phoonnx.
Chatterbox models in ONNX for phoonnx.