Standalone (Ableton Link) + VST3/AU for live performance. 8 tracks, 8 AI models, 30 seconds of patience per loop. It occasionally hallucinates. Not a song generator - you still have to do the work. Stay human.

A node collection for sound design, supporting MusicGen and Stable Audio. Welcome to use and experience it.

seven open source ai music models inside the DAW

Stable Audio LoRA Trainer of salty goodness

Docker image for TTS Generation ALL IN ONE

Portable AI music generator with built-in timeline editor — Stable Audio, one-click install, 100% offline, Windows.

Browser-based AI audio DAW for Stable Audio 3 with text-to-audio, inpainting, LoRA training, FFmpeg effects, waveform editing, sequencer, piano roll, and persistent library.

Python scripts for running stable audio open inference locally and on Modal

a one click windows installer and control center for gary4juce

Local Windows app for Stable Audio Open 1.0 - 9-language UI, multilingual prompt translation, 217 presets across 15 | categories, multi-variations, batch mode, game-ready WAV output. One-file installer.

AI audio generation pipeline with ACE-Step, Stable Audio, and Gradio interface

Docker image for Stable Audio Open 1

Docker service stack for a comprehensive local ai experience, running on a normal home hardware setup with single GPU. DevOps-Dashboards included. WIP.

Docker image for stable-audio-tools: Generative models for conditional audio generation

Real-time AI music generation server for the OBSIDIAN Neural VST plugin. Handles audio generation via a distributed GPU provider network, Stripe Connect revenue sharing, user management, and email automation. Open source under AGPL-3.0.

Python CLI-tool for Stable Audio Open

A pluggable studio tool for AI audio generation. Swap models, keep your workflow.

Portable multi-GPU music generation server for Windows -- 8 models, one-click install, zero dependencies

Marketing website and user dashboard for OBSIDIAN Neural — real-time AI music generation VST3/AU plugin. Presented at AES AIMLA 2025.

Hands-on examples of audio generation using Stable Audio One model with automatic CUDA/CPU device selection