https://vocaroo.com/1f6atW8bYw63

>>939695481
>>939695500
>>939695540
1.
cd ComfyUI/custom_nodes
git clone https://github.com/Enemyx-net/VibeVoice-ComfyUI

2. make a folder for the 1-5B or 7B models, i.e.
ComfyUI\models\tts\VibeVoice\VibeVoice-1.5B
and put all the files from the respective HuggingFace page there
https://huggingface.co/microsoft/VibeVoice-1.5B/tree/main
https://huggingface.co/vibevoice/VibeVoice-7B/tree/main

3.make workflow like in the video from https://github.com/Enemyx-net/VibeVoice-ComfyUI
(pic rel)

select a audio file and start. it will install other stuff
(Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`)
just wait a couple of minutes