Stable Audio Open
Open-weight text-to-audio — 47-second sound effects and music.
Open Source 6–8 GB VRAM
- Min VRAM
- 6 GB
- GPU class
- Entry GPU
- Quant
- FP16
Actually FreeOpen SourceWatermark-FreeHobbyist-Friendly
AudioCraft (MusicGen)
Meta's text-to-music & sound-effect model family.
Open Source 8–16 GB VRAMRuns locally
Actually FreeNo SignupOpen SourceWatermark-FreeHobbyist-Friendly
Visit AudioCraft (MusicGen)Updated 2024-07-19 · Direct link
Hardware requirements
Runs locally · Entry GPU (6–8 GB)
Min VRAM
8 GB
Rec. VRAM
16 GB
Min RAM
16 GB
Rec. RAM
32 GB
Disk
15 GB
GPU class
Entry GPU
11.8+Apple Silicon ✓GPU RequiredQuant: FP16
MusicGen small/medium fits in 8 GB; large needs 16 GB.
Screenshot placeholder · AudioCraft (MusicGen)
What is AudioCraft (MusicGen)?
AudioCraft bundles MusicGen, AudioGen, and EnCodec from Meta FAIR. MusicGen produces 30-second music clips from a text prompt or a melody reference; AudioGen does ambient sound effects. The benchmark OSS baseline for music generation before Stable Audio Open.
Pros & cons
Pros
- Highest-quality OSS music generation for a long time
- Melody conditioning lets you guide the harmony
- EnCodec audio codec included — useful as a building block
Cons
- Weights are non-commercial — research/personal only
- 30-second cap; longer outputs need stitching
- Slower iteration than Stable Audio Open at similar quality
What's actually free?
MIT-licensed code; CC-BY-NC weights (non-commercial).
✓ Actually FreeNo SignupOpen SourceWatermark-Free