Soundbox

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 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.

Hear it

Everything below was generated by Soundbox from the prompt shown. The samples site has around 600 more, each with its prompt and model.

	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
Explosion	underwater explosion, muffled deep concussive thump with a swirling bubble surge and a pressure wave	Stable Audio 3.0 SFX	Listen
Footsteps	footsteps walking on an industrial metal grate walkway, ringing hollow clangs, warehouse reverb	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

Features

• Sound effects. Describe the material, the action and the space and get a clip. Duration, seed, steps, CFG and negative prompt are all exposed, and every generation is saved with its settings so you can regenerate or vary it.
• Music, with or without lyrics. Instrumentals and loops from a style description, or a sung song from a [verse] / [chorus] lyric sheet. Extend a track, cover it in a new style, repaint a section, or split it into drums, bass, vocals and other.
• Speech and voices. Text-to-speech from a script, voice cloning from a short clip or your microphone, and voice conversion. Saved voices live in a Voice Lab and are cast onto the lines of a script.
• A studio. A multi-track timeline with per-track effects, recording, MIDI input, a piano roll and one-click mixdown. A chat assistant beside it turns requests like "mute 1 and 3, add reverb to the vocal" into edits you confirm.
• Built for agents. An MCP server with 21 tools lets Claude Code, Cursor or any MCP client generate, speak, arrange and export audio as part of a larger task. An Agents page logs every call.
• Licences before you download. Each model's licence and commercial-use terms are on its card, and non-commercial weights need an explicit confirmation.
• Optional local helpers. A small local language model can rewrite vague prompts, write lyrics and run the studio chat, and a small image model can draw cover art. Both are off until you turn them on. The assistant can use Ollama or LM Studio instead, and artwork an Automatic1111-compatible server.
• Local and offline. One SQLite file and a folder of WAVs under ~/.soundbox. CUDA, HIP, Metal, Vulkan or CPU, picked automatically. Nothing is uploaded.

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
Voice Lab: clone a voice, then cast it onto script lines	Models: licence and VRAM shown before you download

For agents

Start Soundbox, then add it to your client.

Claude Code

claude mcp add --transport http soundbox http://127.0.0.1:17494/mcp

Cursor and other MCP clients

{ "mcpServers": { "soundbox": { "type": "http", "url": "http://127.0.0.1:17494/mcp" } } }

Then ask for what you need: "add a door slam and a coin pickup sound to this game", "voice these three lines as two characters", "write a 20-second loading-screen loop". The agent gets 21 tools:

Group	Tools	Use
Sound and music	generate, enhance_prompt, separate, list_models, list_sounds, get_sound, delete_sound	One-shot generation. generate waits for the WAV and returns its absolute path. separate splits a track into stems.
Speech	speak, list_voices	A single read.
Stories	create_story, list_stories, get_story, add_lines, update_line, delete_line, split_line, speak_story, mix_track, remove_track, export_story, open_in_studio	A multi-track arrangement the agent builds over several turns and can open in the studio for you to finish.

Three agent skills ship with Soundbox: soundbox-sfx (prompting), soundbox-sound-pass (read a game or app, work out every sound it needs, generate and wire them in) and soundbox-voice-story (write, voice and arrange dialogue). Install them from the Agents page or with soundbox skills install. Connection details, the stdio bridge and the full tool reference are in docs/MCP.md.

Models

Every model runs through audio.cpp, a native runtime, so there is no Python to set up, and switching models is a dropdown, not a new environment. The same prompt and seed on three music models:

Four models are 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

61 more are in the catalog and can be switched on from the Models page:

• Text-to-speech (45): Chatterbox and Chatterbox Turbo, Fish Audio S2 Pro, IndexTTS 2 and 2.5, VibeVoice, Higgs Audio v3, Qwen3-TTS, MOSS TTS, VoxCPM 1 and 2, CosyVoice 3, FireRedTTS3, Maya1, Kokoro, MagpieTTS, Supertonic 3, Pocket TTS and more. Several clone from a reference clip.
• Music (6): ACE-Step 1.5 Base, XL Turbo and XL SFT, 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.

Of these, VibeVoice 1.5B, MiDashengLM-Gen, HTDemucs 6-stem and Chatterbox Turbo have also been run end to end; the others 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). Several are non-commercial, and any model whose licence could not be established is treated as non-commercial. The table 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

The studio

Pick a builder when you start a project. The Script Builder is for dialogue: write lines, cast each to a voice, read them, and arrange the takes. The Music Builder is for tracks and effects: describe one, generate it onto a lane, then extend, cover, split into stems or layer more. Both share the timeline, an eight-effect device rack, MIDI and piano roll, recording, the library and the chat assistant. Export mixes the arrangement down to one new sound. The full guide, with every shortcut, is docs/STUDIO.md.

HTTP API

Everything the app does is available over a local HTTP API 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. The server binds to loopback and has no authentication. Every route is listed in docs/API.md.

Run from source

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. The first run walks you through picking models for your GPU. docs/INSTALL.md covers the command-line tool, environment variables and troubleshooting; docs/DESKTOP.md covers building the desktop app; npm run dev:mock runs the UI with no GPU or server (see CONTRIBUTING.md).

Docker. For a server or NAS, the server and web UI run headless in one container with the audio.cpp runtime already inside: CPU by default, CUDA with an override file.

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

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, or /mcp answers 403. Volumes, GPUs and the details are in docs/INSTALL.md.

Docs

Install	Installing, first run, the CLI, environment variables, troubleshooting
Generating	Writing prompts these models respond to, settings, stems
Studio	The timeline, builders, devices, MIDI, chat and shortcuts
Library	Sessions, projects, tags and where files live
MCP	Connecting agents and every tool
HTTP API	Every route
Desktop	Installers, first launch, building, signing
audio.cpp	The model runtime, backends and adding a model
Architecture	How the pieces fit together

FAQ

Can I sell what I make? It depends on the model. Each model's licence and commercial terms are on its card in the app and in the table above. Stable Audio is free under $1M revenue, ACE-Step 1.5 is MIT, and models with an unestablished licence are marked non-commercial.

Do I need a GPU? No, but CPU generation is slow. A few GB of VRAM covers the verified models, and each model card shows its footprint.

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.

Contributing

Adding a model is a catalog entry, with no new code. Running a listed model and reporting the result helps just as much, since that is how a model becomes verified. See CONTRIBUTING.md.

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. Soundbox downloads weights at your direction and does not redistribute them. The example media under site/public/ was generated with third-party models; its provenance is in ASSETS.md.