9
SoloAudio
π
Extract sounds from audio using text prompts
Generate audio samples using diffusion models
Generate text responses in a chat format
Generate high-fidelity audio from input audio waveforms
Edit audios with text prompts
Python Audio Separator Demo
Get a music sample inspired by the mood of an image
Generate images based on text prompts and condition images
Identify spoken language from audio
Versatile audio super resolution (any -> 48kHz) with AudioSR