- Home
- AI Music Generators
- MusicGen
On the recordRead 12 Oct 202627 facts
MusicGen
On the record
- API
- The documentation says AudioCraft provides a simple API and pretrained MusicGen models.github.com · read 12 Oct 2026
- API and framework
- The repository provides a simple API and documents MusicGen use through the Hugging Face Transformers library.github.com · read 12 Oct 2026
- Audio export formats
- wavaudiocraft.metademolab.com · read 21 Sep 2026
- Audio quality
- The page says a Multi-Band Diffusion EnCodec decoder can reduce audio artifacts at the cost of more computation.audiocraft.metademolab.com · read 12 Oct 2026
- Audio upload
- Yesaudiocraft.metademolab.com · read 21 Sep 2026
- Commercial use
- Noaudiocraft.metademolab.com · read 21 Sep 2026
- Compute requirement
- The documentation says inference with medium-sized models requires a GPU with at least 16 GB of memory.github.com · read 12 Oct 2026
- Hardware requirement
- Running inference with medium-sized models requires a GPU with at least 16 GB of memory, while smaller GPUs can generate short sequences or use the small model for longer sequences.github.com · read 12 Oct 2026
- Known limitations
- The model card says MusicGen cannot generate realistic vocals, performs less well with non-English descriptions, and does not perform equally well across music styles and cultures.github.com · read 12 Oct 2026
- License
- The repository identifies the code as MIT-licensed and the model weights as CC-BY-NC 4.0 licensed.github.com · read 12 Oct 2026
- Licensing
- The code is released under MIT, while the model weights are released under CC-BY-NC 4.0.github.com · read 12 Oct 2026
- Longer tracks
- The maker describes generating tracks up to two minutes by sliding 30-second windows in 10-second chunks while retaining 20 seconds of prior output as context.audiocraft.metademolab.com · read 12 Oct 2026
- Long samples
- The page describes generating two-minute tracks by sliding 30-second windows in 10-second chunks and retaining the previous 20 seconds as context.audiocraft.metademolab.com · read 12 Oct 2026
- Melody guidance
- MusicGen can extract a melody from an input music sample using chromagrams and guide generation to follow it while adhering to a text description.audiocraft.metademolab.com · read 12 Oct 2026
- Model architecture
- MusicGen uses a single-stage Transformer model with an EnCodec tokenizer.github.com · read 12 Oct 2026
- Model design
- MusicGen is a single-stage Transformer language model that generates music using compressed audio tokens.github.com · read 12 Oct 2026
- Model options
- The repository documents small, medium, and large models, as well as melody-conditioned and stereo variants.github.com · read 12 Oct 2026
- Model sizes
- The model card lists 300M, 1.5B, and 3.3B parameter sizes, with text-to-music and melody-guided variants.github.com · read 12 Oct 2026
