generative audio tools for ComfyUI. highly experimental—expect things to break and/or change frequently.

• musicgen text-to-music + audiogen text-to-sound
  • audiocraft and transformers implementations
  • supports audio continuation, unconditional generation
• tortoise text-to-speech
• vall-e x text-to-speech
  • uses korakoe's fork
• voicefixer2
• audio utility nodes
  • save audio, convert audio

# TORCH_CUDA_INDEX_URL=https://download.pytorch.org/whl/cu118  # for cuda 11.8
TORCH_CUDA_INDEX_URL=https://download.pytorch.org/whl/cu121  # for cuda 12.1

cd ComfyUI/custom_nodes
git clone https://github.com/eigenpunk/ComfyUI-audio
cd ComfyUI-audio
pip install -r requirements.txt --extra-index-url $TORCH_CUDA_INDEX_URL

• audio uploads
• audio previews
• prompt weights for text-to-music/audio
• stereo musicgen
• audiogen
• multi-band diffusion
• more/faster tts model support
  • tacotron2
  • vits?
  • vall-e x
  • ???
• split generator nodes by model stages
• more audio generation models
• demucs