Awesome Stable Audio [](https://awesome.re)

August 25, 2026 ยท View on GitHub

A curated list of projects, tools, models, UIs, and resources for Stable Audio. Contributions welcome!

Contents


Official Resources

ResourceDescription
Stable Audio Tools Research RepositoryBackwards-compatible repo for training and inference of all stable audio models
Stable Audio 3 RepositoryOfficial Stable Audio 3 inference and fine-tuning repo
Stable Audio APIOfficial API for Stable Audio
HuggingFace Post-trained ModelsAll official model weights, LoRAs, and spaces.
HuggingFace Base Models, Autoencoders, and OptimizationsAll official model weights, LoRAs, and spaces.
HuggingFace SpaceInteractive online demo on HuggingFace Zero GPU.
Harmonai DiscordCommunity chat and support.
SAME Autoencoder Project PageHigh-quality, stereo audio compression that produces 256-dim continuous latents at 4096x downsampling.
Stable Audio Open Project PageStable Audio Open demo
Stable Audio 3 DocsPrompt guides, fine-tuning, inference, model overview
Stable Audio Tools DocsGeneral Stable Audio docs

Integrations and Extensions

Comfy UI

Fal

LoRA fine-tuning

More from the community

Stable Audio 3

ResourceDescription
Macbook Pro fast inference demoFast inference on Apple Silicon by @dadabots
Promptless Mood steeringSteering Stable Audio 3 by attaching inference-time probes to the diffusion transformer by @gucamporese
DAW PluginJUCE-based DAW plugin by @thepatch_kev
Ableton ExtensionAbleton Live extension by @thepatch_kev
Speech-operated Terminal LooperVoice-controlled terminal looper by @sonic_field
Sample Varations PluginSample variation generation JUCE plugin by @maxgraf__
theDAWBrowser-based DAW for Stable Audio 3 by @gantasmo
LoopMasterA generative loop explorer by @hotghettomusic
SAO-DohFlowEdit implementation to generate intermediate sonic states between a source sample and a target description by team hack-a-lil (Aleksandra Teng Ma, Nithya Shikarpur, Cameron McCoy)
Stable Audio 3 inpainting UIBrowser UI for Stable Audio 3, includes LoRA training with auto-captioning by @_lyraaaa_
StableAudioKitSwift package and CLI for python-less MLX Stable Audio 3 inference on Apple Platforms by @olilarkin
Motif: Maqam generation pluginA LoRA adapter of Stable Audio 3 + JUCE VST plugin for microtonal Arabic maqam music generation by Jad Al Masri, Thiago Santos, Rithik Kundu, Michael Tomasi, and Chris Powers
FragmentaFully-featured, offline desktop app for Stable Audio 3, including LoRA training, audio annotation, and performance mode by @MAz-Codes
neural_tildeMax/MSP package for running Stable Audio 3 locally on Apple Platforms, by @jasper-zheng
LSDJSoftware for using Stable Audio 3 and Magenta RT-2 with Pioneer DDJ-FLX4, by @brxs.
OBSIDIAN NeuralLive performance with Stable Audio 3, by @innermost47
StableGrooveA real-time, hot-swapping, AI-powered drum machine instrument designed for live performance, by @navin-neu and @VincyZed
Unstable DAWAn agentic music studio that transforms a simple hum into an editable production, by @walkingwave, @gilbertotumangday1, and @letaoli123

Papers

YearPaper
2026Stable Audio 3
2026SAME: A Semantically-Aligned Music Autoencoder
2026Low-Resource Guidance for Controllable Latent Audio Diffusion
2025Fast Text-to-Audio Generation with Adversarial Post-Training (Stable Audio Open Small)
2025Stable Audio Open
2024Long-Form Music Generation With Latent Diffusion (Stable Audio 2)
2024Fast Timing-Conditioned Latent Audio Diffusion (Stable Audio)