ComfyUI-HiggsAudio

ComfyUI-HiggsAudio
★ 22

音频合成文本到音频ComfyUI 插件Boson AI 模型
将 Boson AI 的 Higgs Audio v2 文本到音频基础模型整合到 ComfyUI 中，便捷生成高质量语音/音频，以节点化方式在工作流中使用。
💡 在 ComfyUI 工作流中通过文本生成高质量音频。
🍴 2 Forks💻 Python🔄 2025-07-26
📦
网盘下载
复制链接后前往夸克网盘下载
https://pan.quark.cn/s/a9fb3a59e10c
📦 requirements.txt
descript-audio-codec
torch
transformers>=4.45.1,<4.47.0
librosa
dacite
boto3==1.35.36
s3fs
torchvision
torchaudio
json_repair
pandas
pydantic
vector_quantize_pytorch
loguru
pydub
ruff==0.12.2
omegaconf
click
langid
jieba
accelerate>=0.26.0
📄 README

ComfyUI-HiggsAudio

ComfyUI-HiggsAudio is now available in ComfyUI, Higgs Audio v2 is a text-audio foundation model from Boson AI.

Installation

  • Make sure you have ComfyUI installed

  • Clone this repository into your ComfyUI’s custom_nodes directory:
    • cd ComfyUI/custom_nodes
git clone https://github.com/Yuan-ManX/ComfyUI-HiggsAudio.git

  • Install dependencies:
    • cd ComfyUI-HiggsAudio

# Install dependencies
pip install -r requirements.txt
pip install -e .

    Model

    Download Pretrained Models