stable-audio-3

A desktop app to fine-tune, generate and perform live music with diffusion models. Runs on MacOS, Windows and Linux.

ARCHIVED USE theDAW at https://github.com/gantasmo/theDAW - 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.

every stable audio model in ggml for cross-platform and embedded applications, including lora training.

Stable Audio 3 Small Music on iOS with MLX Swift

Agent-operated Stable Audio 3: hardware-aware generation, resumable batches, custom adapters, and continuous audio mixes.

Local Gradio UI for Stable Audio 3 on Apple Silicon (MLX) — generate audio and train LoRAs, no terminal needed. Now blends up to 4 LoRAs at once, each with its own strength and step range. Arcade-styled.

Stable Audio LoRA Trainer of salty goodness

Self-hosted inference server for OBSIDIAN Neural's 9 AI audio engines. Run it on your own GPU (NVIDIA on Windows/Linux, Apple Silicon experimental). No account, no API key, no cloud.

!!! ARCHIVED !!! USE theDAW at https://github.com/gantasmo/theDAW - 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

Fast local audio & music generation studio powered by Stable Audio 3, PyTorch, CUDA, and Gradio.

A pipeline that applies controlled steering at inference time on Stable Audio 3

Stable Audio 3 MLX SPM