Magpie TTS
Collection
Magpie TTS models in ONNX for phoonnx. โข 1 item โข Updated
A Magpie TTS model by NVIDIA, from nvidia/magpie_tts_multilingual_357m, packaged for phoonnx, our ONNX text-to-speech library.
| Architecture | Magpie TTS |
| Upstream | nvidia/magpie_tts_multilingual_357m |
| Author | NVIDIA |
| Languages | ar, fr, it, ko, vi |
| Text input | Unicode codepoints of the text |
pip install --pre phoonnx
import wave
from phoonnx.model_manager import TTSModelManager
manager = TTSModelManager()
manager.load()
manager.merge_default_voices()
voice = manager.voices["magpie/Aria/ar"].load()
with wave.open("output.wav", "wb") as wav_file:
text = "..." # a sentence in ar
voice.synthesize_wav(text, wav_file)
In OVOS, phoonnx installs the ovos-tts-plugin-phoonnx plugin. Select the voice in mycroft.conf:
{"tts": {"module": "ovos-tts-plugin-phoonnx", "ovos-tts-plugin-phoonnx": {"voice": "magpie/Aria/ar"}}}
phoonnx hands the text to scriptconv, our text conversion library, which normalises it and turns it into the model's input:
unicode: UnicodeCodepointPhonemizer from scriptconv.phonemizers.base, in scriptconv itself.magpie/Aria/armagpie/Aria/frmagpie/Aria/itmagpie/Aria/komagpie/Aria/vimagpie/Jason/armagpie/Jason/frmagpie/Jason/itmagpie/Jason/komagpie/Jason/vimagpie/John/armagpie/John/frmagpie/John/itmagpie/John/komagpie/John/vimagpie/Leo/armagpie/Leo/frmagpie/Leo/itmagpie/Leo/komagpie/Leo/vimagpie/Sofia/armagpie/Sofia/frmagpie/Sofia/itmagpie/Sofia/komagpie/Sofia/viThe upstream declares the licence other (nvidia-open-model-license) in the model card of nvidia/magpie_tts_multilingual_357m.