Waveformer uses MusicGen to create music from text and save it as audio or a waveform video.
MusicGen
MusicGen generates music with controls based on text and melody inputs.

About MusicGen
MusicGen is a controllable music generation model supplied with code and models through the AudioCraft PyTorch library for deep learning research on audio generation. It generates music from text descriptions, while melody editions also accept melody input. Local inference requires a GPU, with 16GB of memory recommended for medium sized models.
Pricing is not clearly stated.
Key features
- 10 pre-trained models in small, medium, large and melody sizes
- Stereo tuned variants of small, medium, large, melody and melody large
- Simple API with code examples
- Local Gradio demo
- Jupyter notebook demo at demos/musicgen_demo.ipynb
- Hugging Face Space demo and Colab notebook option
- Use through Transformers library from version 4.31.0
MusicGen at a glance
- Category
- AI & Machine Learning › AI Music Generation
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Details verified
- Oct 22, 2026 · Official source
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
MusicGen alternatives
Tools and sites you could use instead, ranked by how closely they match.
ACE-Step is a local music generation model supporting Mac, AMD, Intel, and CUDA devices.
MusicGen generates an audio track from a music description and can use a short melody as a guide.
AI Jukebox generates an audio clip from a music description, with controls for length, style, and mood.
Generate a soundtrack matching an uploaded image, with controls for denoising steps and eta.
Mubert generates royalty free music from text prompts for online projects.
Popular in AI Music Generation
Well-known listings from the same topic.
Tell us and an editor will check it.
Claim the listing and suggest updates yourself. An editor checks every claim first.












