All tasks / Tools
audio.cpp
Pure C++ ggml inference engine with CLI, server and WebUI that runs 100+ local audio models, including music and Foley models.
- 0xShug0 (community)
- Local only
- Free, open source
Where it ranks
- BMusic generationRuntimes & APIs · Local · via MiniMax Music 3.0
- –Sound effectsRuntimes & APIs · Local · no rated model available here yet
Tools without a benchmark of their own inherit the tier of the best model they offer.
Facts
- Vendor
- 0xShug0 (community)
- Approach
- Runtimes & APIs
- Where it runs
- Runs only on your own hardware
- Interface
- Command line, API, Self-hosted web UI
- Skill level
- Advanced: command line, node graphs or self-hosting
- Price
- Free, open source
- Pricing notes
- Free and open source (GitHub license reported as 'Other'); model weights keep their original licenses.
- Source code
- Open source
- GitHub stars
- 3.6k (19 Oct 2026)
- Last verified
- 19 Oct 2026
Price from github.com, 19 Oct 2026.
Models it gives you
- BMiniMax Music 3.0MiniMax · open weights
- BStable Audio 3 MediumStability AI · open weights
- –ACE-Step 1.5ACE Studio and StepFun · open weights
- –HeartMuLa-oss-3B-happy-new-yearHeartMuLa Team · open weights
- –YuE2 (3B)M-A-P (Multimodal Art Projection) · open weights
- –Stable Audio 3 Small SFXStability AI · open weights
- –ControlFoleyXiaomi (xiaomi-research) · open weights