stable-audio-tools
Stability AIstable-audio-tools is Stability AI's open training and inference library for audio generation models. It trains and runs latent diffusion models such as Stable Audio Open, the Dance Diffusion waveform models and the audio autoencoders they decode with, from JSON model and dataset configurations, with LoRA fine-tuning and a Gradio interface for trying a trained model.
Scored as the library. The Stable Audio weights it loads are their own entry, stable-audio, under Stability's community license; the newer Stable Audio 3 models ship their own pipeline in a separate repository.
Openness
5 high confidence- license
- MIT (OSI; the stable-audio-tools code. The third-party code it vendors, under LICENSES/, is MIT as well where read)
- source
- public (Stability-AI/stable-audio-tools)
- core features withheld
- no — no ee, enterprise, commercial or proprietary path; Stability sells its largest audio model through a separate API and enterprise offering, not as an edition of this library
The library is MIT-licensed and fully public, training code included. Stability AI's paid audio offering is a hosted model, not a closed edition of this code.
- https://raw.githubusercontent.com/Stability-AI/stable-audio-tools/main/LICENSE recorded 2026-11-12
LICENSE body: "MIT License / Copyright (c) 2023 Stability AI".
- https://raw.githubusercontent.com/Stability-AI/stable-audio-tools/main/LICENSES/LICENSE_META.txt recorded 2026-11-12
Vendored-code license LICENSES/LICENSE_META.txt: "MIT License / Copyright (c) Meta Platforms, Inc. and affiliates."
- https://raw.githubusercontent.com/Stability-AI/stable-audio-tools/main/LICENSES/LICENSE_NVIDIA.txt recorded 2026-11-12
Vendored-code license LICENSES/LICENSE_NVIDIA.txt: "MIT License / Copyright (c) 2022 NVIDIA CORPORATION."
- https://stability.ai/news-updates/meet-stable-audio-3-the-model-family-built-for-artistic-experimentation-with-open-weight-models recorded 2026-11-12
Stability AI announcement: "Stable Audio 3.0 Large is available via the Stability AI API and self-hosting for enterprise deployments", a hosted offering separate from the open code.
- https://ungh.cc/repos/Stability-AI/stable-audio-tools/files/main recorded 2026-11-12
Full file list of the main branch: stable_audio_tools/ (models, training, inference, interface), train.py, docs/ and LICENSES/; no ee/, enterprise/, commercial/ or proprietary/ path.
Adoption
1 high confidenceAdoption is measured as PyPI downloads of the stable-audio-tools package, published by Stability AI. The README's main install path clones the repository, which is not counted.
- https://pypi.org/pypi/stable-audio-tools/json recorded 2026-11-12
PyPI stable-audio-tools 0.0.20, uploaded 2026-05-20: author "Stability AI", summary "Training and inference tools for generative audio models from Stability AI".
- https://pypistats.org/api/packages/stable-audio-tools/recent recorded 2026-11-12
pypistats for stable-audio-tools: last_month 2244.
Capability
2 high confidencestable-audio-tools trains and runs more than one family of audio generation models, as AudioCraft does, and like it covers audio alone.
- https://raw.githubusercontent.com/Stability-AI/stable-audio-tools/main/README.md recorded 2026-11-12
README: "Training and inference code for audio generation models"; a Gradio interface for stabilityai/stable-audio-open-1.0; train.py for training and fine-tuning.
- https://ungh.cc/repos/Stability-AI/stable-audio-tools/files/main recorded 2026-11-12
Model configs: txt2audio/stable_audio_1_0.json and stable_audio_2_0.json, four dance_diffusion configs, and autoencoder configs for Stable Audio 1.0 and 2.0; a models/lora package.
Verified 2026-11-12, except some scores, still awaiting re-confirmation