Stable diffusion for real-time music generation

Generate music from a prompt or melody

🔊 Text-Prompted Generative Audio Model

Generate speech from text, clone voices from mp3 files. From James Betker AKA "neonbjb".

Four-bar drum loop generation

Text-to-audio generation with latent diffusion models

Bach chorale generation and harmonization

Tools to train a generative model on arbitrary audio samples

Music inpainting of melody and chords

AudioSR: Versatile Audio Super-resolution at Scale

Emotional conditioned music generation using transformer-based model.