VibeVoice 7B for ComfyUI

Single-file checkpoints of Microsoft VibeVoice 7B (VibeVoice-Large) for the native ComfyUI node pack Aero-Ex-ComfyUI-Vibevoice. They do not load in the original vibevoice package or in transformers.

File	Size	Notes
`vibevoice_7b_bf16.safetensors`	17.6 GB	Full precision reference.
`vibevoice_7b_int8_convrot.safetensors`	10.5 GB	INT8 ConvRot (per-channel, group 256) weights. Recommended for GPUs under 16 GB.

Put one in ComfyUI/models/text_encoders/ and load it with Load VibeVoice Model.

Conversion

The weights are the original VibeVoice-Large weights, repacked into one file with the tokenizer and config:

attention Q/K/V and MLP gate/up projections merged,
LM head pruned to the four speech control tokens,
INT8 file quantized with comfy-kitchen's TensorWiseINT8 ConvRot layout from the bf16 file.

Checked against the transformers VibeVoice implementation: identical prompt and generated speech tokens with matched noise.

Usage

Speaker 1: Welcome back to the podcast.
Speaker 2: Thanks, it is great to be here.

Connect one 5–15 s voice sample per speaker. The model was trained on up to 4 speakers.

License and responsible use

MIT, as the original release. VibeVoice can clone voices: only use voices you have permission to use, and disclose AI-generated audio. See Microsoft's model card for the original risks and limitations.

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for Aero-Ex/ComfyUI-Vibevoice

Base model

aoi-ot/VibeVoice-Large

Finetuned

(2)

this model