Text-to-Speech
Vui
English
tts
speech-synthesis
voice-cloning
streaming
conversational
qwen3-tts
conversational-speech
context-aware
cpu-inference
on-device
small-model
Instructions to use fluxions/vui with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Vui
How to use fluxions/vui with Vui:
# !pip install git+https://github.com/fluxions-ai/vui import torchaudio from vui.legacy import Vui, render model = Vui.from_pretrained().cuda() waveform = render( model, "Hey, here is some random stuff, usually something quite long as the shorter the text the less likely the model can cope!", ) print(waveform.shape) torchaudio.save("out.wav", waveform[0], 22050) - Notebooks
- Google Colab
- Kaggle
Download vui-cohost-100m.pt from fluxions/vui: direct link, hf CLI and curl.
- Browser
- Download file 198 MB
-
https://huggingface.co/fluxions/vui/resolve/main/vui-cohost-100m.pt
- Command line
-
hf download hf://fluxions/vui/vui-cohost-100m.pt
-
curl -L -o vui-cohost-100m.pt https://huggingface.co/fluxions/vui/resolve/main/vui-cohost-100m.pt
198 MB
- Xet hash:
- 167e97950ef082b0ce35e1327814febeb87f268d4ae0745171ced243c8c3976c
- Size of remote file:
- 198 MB
- SHA256:
- 50b0a39df74b059dc544beed60f838734c62d29504afa170ca576abb4a7125f5
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.