hamsanders/soundbox
Developer toolsFree, open-source, local alternative to ElevenLabs and Suno. AI sound effects, music with lyrics, text-to-speech and voice cloning on your own GPU (Stable Audio, ACE-Step and more).
Overview
AI sound effects, music, text-to-speech and voice cloning, generated on your own GPU. Describe a sound and get a WAV. Write lyrics and get a song. Clone a voice from a short clip. Arrange it all on a timeline, or let Claude Code, Cursor or any MCP agent do it for you. Open-weight models, no account, no credits, works offline. MIT licensed. The 30-second tour · Under the hood: no Python, swap models, real timings The installers carry their own runtime, so nothing else needs installing. Models download from inside the app the first time you use them. The builds are not signed yet, so the first launch asks you to confirm: docs/DESKTOP.md shows where. Linux, or running from source or in Docker: see Run from source. Everything below was generated by Soundbox from the prompt shown. The samples site has around 600 more, each with its prompt and model. - Describe the material, the action and the space and get a clip.
README
Describe it, hear it, arrange it
| Make | Arrange | Connect |
|---|---|---|
| Sound effects and ambience from a description | A multi-track timeline with effects, MIDI and mixdown | An MCP server with 24 tools for Claude Code and Cursor |
| Instrumentals, or songs from a lyric sheet | Cast saved voices onto the lines of a script | A local HTTP API on port 17494 |
| Speech, voice cloning and voice conversion | Extend, cover, repaint, split into stems | Three agent skills, including a full sound pass |
Four models are verified end to end and on by default; 61 more can be switched
on from the Models page. Each model’s licence is shown before you download it.
Everything stays in one SQLite file and a folder of WAVs under ~/.soundbox.
Profiles give you several libraries in one install, one per game or client,
switched from the header without a restart; the models are shared.
Download
| Platform | Installer |
|---|---|
| Windows 10 and 11 (x64) | Soundbox_x.y.z_x64-setup.exe |
| macOS, Apple silicon | Soundbox_x.y.z_aarch64.dmg |
| macOS, Intel | Soundbox_x.y.z_x64.dmg |
The installer carries its own runtime. The builds are not signed yet, so the first launch asks you to confirm (where). Open SFX, describe the material, the action and the space, and generate: the first model downloads when you pick it, with its licence shown first.
| Hardware | What to expect |
|---|---|
| NVIDIA GPU (Windows, Linux) | CUDA. A few GB of VRAM covers the verified models; MiniMax Music 3 wants about 10 GB. |
| AMD or Intel GPU | Runs on the CPU unless you set SOUNDBOX_AUDIOCPP_BACKEND=vulkan (how). Vulkan is not yet confirmed on the verified models; reports welcome. |
| Apple silicon | Metal. Installers exist; none of the verified models has been confirmed on a Mac yet. |
| No dedicated GPU | Works, slowly. A clip that takes seconds on a GPU takes minutes on the CPU. |
Linux, Docker and running from source are under Run from source.
Install with a prompt
Paste this into Claude Code, Cursor or Codex:
Install Soundbox on this machine and confirm it works, following
https://github.com/HamSanders/soundbox/blob/main/docs/INSTALL-AGENT.md
The guide tells the agent to check the GPU and VRAM first, to show you each model’s size and licence before downloading it, never to accept a non-commercial licence for you, and to finish by generating one sound and telling you where the WAV is.
Hear it
Each clip was generated by Soundbox from the prompt shown. The samples site has around 600 more.
| Prompt | Model | ||
|---|---|---|---|
| Glass | large window pane breaking, cracking then collapsing inward with long shards falling and shattering on a wooden floor | Stable Audio 3.0 SFX | ▶ Listen |
| Ambience | heavy thunderstorm, driving rain with rolling thunder and wind gusting through trees, outdoor, seamless loop | Stable Audio 3.0 SFX | ▶ Listen |
| Game | plasma bolt firing, thick electric discharge with a downward pitch sweep and a crackling tail | Stable Audio 3.0 SFX | ▶ Listen |
| Instrumental | 1980s synthwave arcade title theme, wide analog saw lead, gated reverb drum machine, pulsing sidechained bass, 110 BPM | Stable Audio 3.0 Small Music | ▶ Listen |
| Song | triumphant power pop victory anthem, bright electric guitars, punchy live drums, gang vocal chorus, with a four-line lyric sheet | ACE-Step 1.5 | ▶ Listen |
For agents
Start Soundbox, then add it to your client.
claude mcp add --transport http soundbox http://127.0.0.1:17494/mcp
Cursor and other MCP clients take { "type": "http", "url": "http://127.0.0.1:17494/mcp" }.
Then ask: “add a door slam and a coin pickup to this game”, “voice these three
lines as two characters”, “write a 20-second loading-screen loop”. The agent
gets 24 tools for sounds, speech and multi-track stories, and three skills:
soundbox-sfx, soundbox-sound-pass and soundbox-voice-story. Every tool,
the stdio bridge and the skills are in docs/MCP.md.
Models
Every model runs through audio.cpp, a native runtime, so there is no Python to set up. Verified end to end and on by default:
| Model | Good for | Licence | Commercial use |
|---|---|---|---|
| Stable Audio 3.0 SFX | Sound effects, foley, ambience | Stability AI Community | ⚠️ Under $1M revenue |
| Stable Audio 3.0 Small Music | Instrumental music, loops | Stability AI Community | ⚠️ Under $1M revenue |
| ACE-Step 1.5 Turbo | Songs with lyrics; extend, cover, repaint | MIT | ✅ Yes |
| MiniMax Music 3 | Songs with lyrics, about 10 GB VRAM | MiniMax-Music3 Community | ⚠️ Conditional |
Any model whose licence could not be established is treated as non-commercial. This is a summary, not legal advice: read each licence before you ship what a model made.
Compared with a hosted service
| Hosted (ElevenLabs, Suno and similar) | Soundbox | |
|---|---|---|
| Runs on | Their GPUs | Your machine |
| Cost | Subscription or credits | Your electricity |
| Account | Required | None |
| Models | Closed, tuned, consistent | Open weights; quality varies by model |
| Output rights | Their terms of service | The licence of the model that made it, shown up front |
| Offline | No | Yes, once the weights are downloaded |
| Agents | HTTP API | HTTP API and an MCP server |
| Source | Closed | MIT |
Run from source
Docs
| If you want to | Read |
|---|---|
| Get it running, or fix a first run | Install · Desktop |
| Write prompts these models answer | Generating |
| Arrange, mix and export | Studio · Library |
| Drive it from an agent or a script | MCP · HTTP API |
| Add or verify a model | audio.cpp · Contributing |
| Understand how the pieces fit | Architecture |
FAQ
Can I sell what I make? It depends on the model. Stable Audio is free under $1M revenue, ACE-Step 1.5 is MIT, and models with an unestablished licence are marked non-commercial. Each model’s terms are on its card in the app.
Do I need a GPU? No, but CPU generation is slow. The hardware table above says what to expect.
Does it work on a Mac? There are installers for Apple silicon and Intel, and audio.cpp runs on Metal. None of the verified models has been confirmed on a Mac yet, so reports are welcome.
How do I remove it? Delete the app and ~/.soundbox. There is no account
to close and nothing was uploaded.
Licence
Soundbox is MIT. The model weights are not: each carries its own
licence, and what you can do with generated audio is governed by the licence of
the model that made it. Clone only voices you have permission to use. Soundbox
downloads weights at your direction and does not redistribute them. Example
media under site/public/ was generated with third-party models; its
provenance is in ASSETS.md.
Install
This server does not publish a one-line install command.
Open the repository installation guide New to MCP? Start with the mcpskill.org guide →