Get stable-audio-3 on Windows, macOS or Linux Now!
Open-source developer tool with a documented one-command setup.
Get stable-audio-3 with one command
Pick your system, reveal the step-by-step guide, copy the command, paste it into your terminal and press Enter. This command was taken from the project's own documentation and checked against it.
Not available for Windows yet.
stable-audio-3 doesn't publish an install command for Windows anywhere we can verify, so there's nothing for us to show you. We won't invent one. It does document one for macOS and Linux — switch to that tab.
Pastes into PowerShell and installs stable-audio-3 on your Windows machine in one step — no manual setup, no build tools. It fetches the project's own install script and runs it, which is the standard way these tools ship — worth a read if you like to know what's running.
Not available for macOS yet.
stable-audio-3 doesn't publish an install command for macOS or Linux anywhere we can verify, so there's nothing for us to show you. We won't invent one. It does document one for Windows — switch to that tab.
Pastes into your terminal and installs stable-audio-3 on your macOS or Linux machine in one step — no manual setup, no build tools. It fetches the project's own install script and runs it, which is the standard way these tools ship — worth a read if you like to know what's running.
How to set up stable-audio-3, step by step
On Windows, open PowerShell (press Win, type PowerShell, hit Enter) and paste the command. On macOS or Linux, open Terminal — on a Mac it's in Applications ▸ Utilities, or press Cmd+Space and type Terminal — and paste the command there.
Run stable-audio-3 --help to see the available commands, and
stable-audio-3 --version to confirm the install worked. If your shell complains about
permissions, that project usually documents a corrected command on its own site.
This asks PowerShell to download a small installer script from the project, then execute it in memory. Nothing is saved to disk. The script is the project's own, but it's worth reading it first — that's why there's a note above.
What stable-audio-3 does
- Fast, state-of-the-art generation - Generate minutes of audio in milliseconds
- Three inference modes — text-to-audio, audio-to-audio editing, and inpainting/continuation
- Variable-length generation — handles generation of a variety of sequences without wasting inference time and VRAM on unused latents
- Broad hardware support — CPU (Small), CUDA/TensorRT (Medium), Apple Silicon via CoreML, Others coming soon
- set to your GPU's compute capability: (A100), (A10/RTX 3090), (L4/RTX 4090), (H100/H200)
- number of parallel compile jobs; 4–8 is typical, reduce if you run out of RAM during compilation
Summarised from stable-audio-3's own README.
About stable-audio-3
Open-source developer tool with a documented one-command setup.
| Category | Command-line tool |
|---|---|
| Install method | PowerShell one-liner (irm | iex) |
| Windows | documented install command available |
| macOS / Linux | documented install command available |
| Price | Free and open source |
| Command verified | Yes — checked against the project README |
| Popularity | 776 stars on the project's public repository |
On mobile
stable-audio-3 is a command-line tool, so there is no phone app for it — a phone has no shell to run it in. You'll need a desktop, or a remote shell into a machine that has one.
stable-audio-3 is developed by its own authors. This page is an independent reference; we are not affiliated with or sponsored by the project. The command shown here was reproduced from the project's public documentation — always check the project's own documentation before running anything.