<div align="center">

Soundbox

The free, open-source, local alternative to ElevenLabs and Suno.

Sound effects, music, songs with lyrics, speech and voice cloning from open-weight models on your own GPU. Arrange it on a timeline, or let Claude Code, Cursor or any MCP agent do it. No account, no credits, works offline. MIT.

Download · Hear it · For agents · Models · Docs · Website

<img src="site/public/product/same-prompt-three-models.gif" alt="The same prompt and seed rendered by Stable Audio 3.0 Small Music, MiniMax Music 3 and ACE-Step 1.5 Turbo, with measured render times on an RTX 5080" width="880">

Watch: 30-second tour · Under the hood · Agents and MCP

</div>

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 21 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.

<details> <summary><b>Screenshots</b> · studio, music, SFX, Voice Lab, models</summary> <br> <img src="site/public/product/studio.png" alt="The Soundbox studio: a script cast across three speakers above a multi-track timeline holding the spoken lines, an ambient music bed and sound effects, with the library panel on the right" width="880">

| | | |---|---| | <img src="site/public/product/music-studio.png" alt="The Music page: a request form with model, licence, styles, tempo, key and length beside a shelf of generated takes"> | <img src="site/public/product/sfx.png" alt="The SFX library with waveforms, models and seeds, and the prompt composer"> | | Music. A style prompt or a lyric sheet in, a shelf of takes out. | Sound effects. Every take kept with its prompt, model and seed. | | <img src="site/public/product/voice-lab.png" alt="The Voice Lab: saved voices as cards, cloned from a clip or built into a model"> | <img src="site/public/product/models.png" alt="The Models page: each model with its licence badge, size and install state"> | | Voice Lab. Clone a voice, then cast it onto script lines. | Models. Licence and VRAM shown before you download. |

</details>

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 21 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.

<img src="site/public/product/agents.png" alt="The Agents page: connected MCP clients, copy-paste connection commands, and a log of recent calls" width="880">

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 |

<details> <summary><b>61 more in the catalog</b> · 45 text-to-speech, 6 music, 2 SFX, 4 stem separation, 4 voice conversion</summary> <br>

| Kind | Count | Includes | |---|---|---| | Text-to-speech | 45 | Chatterbox, Fish Audio S2 Pro, IndexTTS 2, VibeVoice, Higgs Audio v3, Qwen3-TTS, CosyVoice 3, Kokoro and more; several clone from a reference clip | | Music | 6 | ACE-Step 1.5 Base and XL, Stable Audio 3.0 Medium, HeartMuLa, MiniMax H3 | | Sound effects | 2 | MiDashengLM-Gen, ControlFoley | | Stem separation | 4 | HTDemucs (4- and 6-stem), BS-RoFormer, Mel-Band RoFormer | | Voice conversion | 4 | RVC, Seed-VC, MioCodec, MeanVC2 |

VibeVoice 1.5B, MiDashengLM-Gen, HTDemucs 6-stem and Chatterbox Turbo have also been run end to end; the rest are marked unverified until someone reports. The 19 added in October 2026 need audio.cpp 0.9.2 or newer (soundbox model install audiocpp fetches the latest).

</details>

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

<details> <summary><b>Node, Docker and the HTTP API</b></summary> <br>

Requires Node 22.12 or later. No Python, no CUDA toolkit.

git clone https://github.com/HamSanders/soundbox
cd soundbox
npm install
npm run dev

This starts the server on port 17494 and the UI on http://localhost:5174. npm run dev:mock runs the UI with no GPU or server (see CONTRIBUTING.md).

Docker. The server and web UI run headless in one container with the audio.cpp runtime inside. CPU by default; add the CUDA override for a GPU. Both pull the prebuilt image from GHCR (:latest, :cuda, or a version such as :v0.4.0 and :v0.4.0-cuda).

docker compose up -d
docker compose -f docker-compose.yml -f docker-compose.cuda.yml up -d

To build from the checkout instead, add -f docker-compose.build.yml (and -f docker-compose.build-cuda.yml for CUDA) and --build; see docs/INSTALL.md.

There is no authentication, so keep the port on localhost or behind a reverse proxy that has some, and set SOUNDBOX_ALLOWED_HOSTS to the name you reach it by. Details are in docs/INSTALL.md.

HTTP API. Everything the app does is available on port 17494:

curl -X POST http://127.0.0.1:17494/api/generate \
  -H 'Content-Type: application/json' \
  -d '{"model":"audiocpp-stable-audio-3-sfx","prompt":"heavy wooden door slamming in a stone corridor","duration_s":3}'

Long jobs return an id with a server-sent event stream. Every route is in docs/API.md.

</details>

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,