soundbox

<div align="center"> # Soundbox **Sound effects, music and voices, generated on your own machine.** 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 your coding agent do it over MCP. Open-weight models, no account, works offline. [](https://github.com/Gadurp1/soundbox/releases/latest) [](https://github.com/Gadurp1/soundbox/releases) [](LICENSE) [](docs/MCP.md) [](#download) [Download](#download) · [Hear it](#hear-it) · [Features](#features) · [For agents](#for-agents) · [Models](#models) · [Docs](docs/) <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="900"> </div> ## Download | Platform | Installer | |---|---| | **Windows** 10 and 11 (x64) | [`Soundbox_x.y.z_x64-setup.exe`](https://github.com/Gadurp1/soundbox/releases/latest) | | **macOS**, Apple silicon | [`Soundbox_x.y.z_aarch64.dmg`](https://github.com/Gadurp1/soundbox/releases/latest) | | **macOS**, Intel | [`Soundbox_x.y.z_x64.dmg`](https://github.com/Gadurp1/soundbox/releases/latest) | 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](docs/DESKTOP.md#installing) shows where. Linux, or running from source: see [Run from source](#run-from-source). ## Hear it Everything below was generated by Soundbox from the prompt shown. The [samples site](https://gadurp1.github.io/soundbox/sfx/) has around 600 more, each with its prompt, model and seed. | | 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](https://gadurp1.github.io/soundbox/sfx/glass/glass-window-pane-break) | | Explosion | *underwater explosion, muffled deep concussive thump with a swirling bubble surge and a pressure wave* | Stable Audio 3.0 SFX | [Listen](https://gadurp1.github.io/soundbox/sfx/explosion/explosion-underwater) | | Footsteps | *footsteps walking on an industrial metal grate walkway, ringing hollow clangs, warehouse reverb* | Stable Audio 3.0 SFX | [Listen](https://gadurp1.github.io/soundbox/sfx/footsteps/footsteps-metal-grate) | | Ambience | *heavy thunderstorm, driving rain with rolling thunder and wind gusting through trees, outdoor, seamless loop* | Stable Audio 3.0 SFX | [Listen](https://gadurp1.github.io/soundbox/sfx/rain/rain-thunderstorm-full) | | Game | *plasma bolt firing, thick electric discharge with a downward pitch sweep and a crackling tail* | Stable Audio 3.0 SFX | [Listen](https://gadurp1.github.io/soundbox/sfx/laser/laser-plasma-bolt) | | 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](https://gadurp1.github.io/soundbox/music/neon-arcade-nights) | | 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](https://gadurp1.github.io/soundbox/music/victory-lap) | ## 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. <table> <tr> <td><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"></td> <td><img src="site/public/product/sfx.png" alt="The SFX library with waveforms, models and seeds, and the prompt composer"></td> </tr> <tr> <td align="center">Music: a style prompt or a lyric sheet in, a shelf of takes out</td> <td align="center">Sound effects: every take kept with its prompt, model and seed</td> </tr> <tr> <td><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"></td> <td><img src="site/public/product/models.png" alt="The Models page: each model with its licence badge, size and install state"></td> </tr> <tr> <td align="center">Voice Lab: clone a voice, then cast it onto script lines</td> <td align="center">Models: licence and VRAM shown before you download</td> </tr> </table> ## For agents Start Soundbox, then add it to your client. **Claude Code** ```bash claude mcp add --transport http soundbox http://127.0.0.1:17494/mcp ``` **Cursor and other MCP clients** ```json { "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](docs/MCP.md). <p align="center"> <img src="site/public/product/agents.png" alt="The Agents page: connected MCP clients, copy-paste connection commands, and a log of recent calls with tool, client, prompt, duration and sounds produced" width="900"> </p> ## Models Every model runs through [audio.cpp](docs/AUDIOCPP.md), a native runtime, so there is no Python to set up. 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 | 42 more are in the catalog and can be switched on from the Models page: - **Text-to-speech (33):** Chatterbox, Fish Audio S2 Pro, IndexTTS 2 and 2.5, VibeVoice, Higgs Audio v3, Qwen3-TTS, MOSS TTS, VoxCPM 2, Supertonic 3, Pocket TTS and more. Several clone from a reference clip. - **Music:** ACE-Step 1.5 Base, Stable Audio 3.0 Medium, HeartMuLa, MiniMax H3. - **Stem separation:** HTDemucs, BS-RoFormer, Mel-Band RoFormer. - **Voice conversion:** RVC, Seed-VC, MioCodec. Of these, VibeVoice 1.5B has also been run end to end; the others are marked unverified until someone reports. 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](docs/STUDIO.md). ## HTTP API Everything the app does is available over a local HTTP API on port 17494. ```bash 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](docs/API.md). ## Run from source Requires Node 22.12 or later. No Python, no CUDA toolkit. ```bash git clone https://github.com/Gadurp1/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](docs/INSTALL.md) covers the command-line tool, environment variables and troubleshooting; [docs/DESKTOP.md](docs/DESKTOP.md) covers building the desktop app; `npm run dev:mock` runs the UI with no GPU or server (see [CONTRIBUTING.md](CONTRIBUTING.md)). ## Docs | | | |---|---| | [Install](docs/INSTALL.md) | Installing, first run, the CLI, environment variables, troubleshooting | | [Generating](docs/GENERATING.md) | Writing prompts these models respond to, settings, stems | | [Studio](docs/STUDIO.md) | The timeline, builders, devices, MIDI, chat and shortcuts | | [Library](docs/LIBRARY.md) | Sessions, projects, tags and where files live | | [MCP](docs/MCP.md) | Connecting agents and every tool | | [HTTP API](docs/API.md) | Every route | | [Desktop](docs/DESKTOP.md) | Installers, first launch, building, signing | | [audio.cpp](docs/AUDIOCPP.md) | The model runtime, backends and adding a model | | [Architecture](docs/ARCHITECTURE.md) | 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](CONTRIBUTING.md). ## Licence Soundbox is [MIT](LICENSE). 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](ASSETS.md).