Moûsai
Text-to-music generation model using cascaded latent diffusion.
About
Mousai is a research text-to-music model that uses cascaded latent diffusion to generate long-form stereo music at 48 kHz from text descriptions. It is built on the audio-diffusion-pytorch library, a customizable waveform-based diffusion toolkit covering unconditional and text-conditional generation, diffusion autoencoding, upsampling, and vocoding. The library is provided for PyTorch; pretrained weights follow the paper's configuration. Open-source research release.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Music & Audio Generation
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Advanced (4/5)
- Minimum VRAM
- 8 GB
- Added
- Apr 3, 2026
Related Tools
Fast music generation model producing full songs with lyrics in seconds.
Open-source toolkit for audio, music, and speech generation research.
Original latent diffusion model for text-to-audio generation.
State-of-the-art music source separation model by Meta for splitting tracks.
High-fidelity neural audio codec by Meta for audio compression and tokenization.
Updated music generation model with improved quality and longer generation.