We and selected third parties use cookies or similar technologies for technical purposes and, with your consent, to analyze how the site is used.

You can freely give, refuse or withdraw your consent at any time.

Audio Studio

MCP server by KanaWorks_AI

Generate, edit and loop background music and sound effects locally with Stable Audio 3 on Apple Silicon or NVIDIA GPUs

Runs locally (Runs on your machine: its page has the install command)Runs with uvx

Install Audio Studio

Runs on your machine. Your client starts it with this command:

uvx --python 3.11 audio-studio-mcp --torch-backend cu126

Needs uv (Python) on your computer. The setup steps below show where the command goes in each client.

  • AUDIO_STUDIO_OUTPUT_DIR optional Folder for generated audio (default: ~/AudioStudio)
  • AUDIO_STUDIO_SA3_MODEL optional Model: medium (default, best quality), sm-music or sm-sfx (small and fast)
  • AUDIO_STUDIO_IDLE_UNLOAD_MIN optional Minutes without a request before the model is freed from memory (0 = never)

Share this server

Opens this page, with the install command and setup steps.

mcp.tc/i/audio-studio

About

Audio Studio gives an MCP client a local sound studio. You describe background music, instrument loops or sound effects in plain language, and the server generates them with Stable Audio 3. It can also restyle a clip, regenerate a time range, extend a track, make seamless loops, apply fades, normalize loudness and export WAV, OGG or FLAC files. Each file gets a JSON sidecar with its prompt, seed and settings.

It runs as a local stdio package started with uvx (PyPI package audio-studio-mcp). Nothing is uploaded, and no cloud service or API key is needed. It requires uv, ffmpeg, and either an Apple Silicon Mac (MLX) or a Windows PC with an NVIDIA GPU (PyTorch). Windows also needs a free Hugging Face account to accept the model license.

What you can do

  • Generate background music, instrument loops and sound effects from a text prompt
  • Produce 1 to 4 candidates per call
  • Re-style a clip, regenerate a time range or extend a track
  • Create seamless loops and apply fades
  • Normalize loudness (LUFS) and export 48 kHz WAV, OGG or FLAC
  • Save a JSON sidecar with prompt, seed and settings for reproducibility

Tools

Local servers list their tools once they’re running, and this one doesn’t publish its list in advance. Your client shows them after you add it.

Example prompts

  • Make a 30 second lo-fi cafe background track at 85 BPM

  • Generate a glass bottle shattering on a concrete floor sound effect

  • Extend this 20 second synthwave track to 40 seconds

  • Turn this track into a seamless loop and normalize the loudness

Set up

Every client starts Audio Studio on your machine with the same command. Pick yours; the page remembers your choice.

Claude Code

  1. Run this in a terminal, in your project folder:
claude mcp add --transport stdio audio-studio -- uvx --python 3.11 audio-studio-mcp --torch-backend cu126
  1. Start Claude Code and type /mcp. audio-studio should show as connected.

Add --scope user to make it available in every project.

Claude Desktop

  1. Open Settings → Developer → Edit Config. It opens claude_desktop_config.json. Add:
claude_desktop_config.json
{
  "mcpServers": {
    "audio-studio": {
      "command": "uvx",
      "args": [
        "--python",
        "3.11",
        "audio-studio-mcp",
        "--torch-backend",
        "cu126"
      ]
    }
  }
}
  1. Save the file and restart Claude Desktop.

Needs uv (Python) on your computer. The file lives in ~/Library/Application Support/Claude/ on macOS and %APPDATA%\Claude\ on Windows.

Cursor

Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):

mcp.json
{
  "mcpServers": {
    "audio-studio": {
      "command": "uvx",
      "args": [
        "--python",
        "3.11",
        "audio-studio-mcp",
        "--torch-backend",
        "cu126"
      ]
    }
  }
}

Needs uv (Python) on your computer.

VS Code

Or from a terminal:

code --add-mcp '{"name":"audio-studio","type":"stdio","command":"uvx","args":["--python","3.11","audio-studio-mcp","--torch-backend","cu126"]}'

Or commit it to the repo in .vscode/mcp.json:

.vscode/mcp.json
{
  "servers": {
    "audio-studio": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "--python",
        "3.11",
        "audio-studio-mcp",
        "--torch-backend",
        "cu126"
      ]
    }
  }
}

Needs uv (Python) on your computer.

Devin Desktop

  1. Add it to ~/.config/devin/mcp_config.json (macOS and Linux) or %APPDATA%\devin\mcp_config.json (Windows):
mcp_config.json
{
  "mcpServers": {
    "audio-studio": {
      "command": "uvx",
      "args": [
        "--python",
        "3.11",
        "audio-studio-mcp",
        "--torch-backend",
        "cu126"
      ]
    }
  }
}
  1. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf.

Codex

codex mcp add audio-studio -- uvx --python 3.11 audio-studio-mcp --torch-backend cu126

Or edit ~/.codex/config.toml directly:

config.toml
[mcp_servers.audio-studio]
command = "uvx"
args = ["--python", "3.11", "audio-studio-mcp", "--torch-backend", "cu126"]

Needs uv (Python) on your computer.

Gemini CLI

gemini mcp add audio-studio uvx -- --python 3.11 audio-studio-mcp --torch-backend cu126

This adds it to the current project. Add -s user to use it everywhere.

Any client

Most clients that start local servers accept this shape:

{
  "mcpServers": {
    "audio-studio": {
      "command": "uvx",
      "args": [
        "--python",
        "3.11",
        "audio-studio-mcp",
        "--torch-backend",
        "cu126"
      ]
    }
  }
}

Zed puts servers under context_servers in its settings, with the same command, args and env fields.

Needs uv (Python) on your computer.

Embed

Show Audio Studio in a README or on your site. Each embed links to this page, uses the server’s own install command, and sets no cookies. How embeds work

The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.

README badge

Badge preview, lightBadge preview, dark
Markdown
[![Audio Studio on mcp.tc](https://mcp.tc/i/audio-studio/badge.svg)](https://mcp.tc/i/audio-studio)
HTML
<a href="https://mcp.tc/i/audio-studio"><img src="https://mcp.tc/i/audio-studio/badge.svg" alt="Audio Studio on mcp.tc" height="20"></a>

It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.

Website card

HTML
<script src="https://mcp.tc/w/audio-studio.js" async></script>

The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.

iframe

HTML
<iframe src="https://mcp.tc/embed/audio-studio" title="Audio Studio on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>

Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.

JSON

The listing as data for your own pages and tools: name, tagline, install command, tools and the “Add to” links. Any site can read it (CORS is open).

https://mcp.tc/i/audio-studio.json

What each field means

AI prompt

Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the Audio Studio card to your site.

Markdown
Add the mcp.tc card for Audio Studio, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.

Put this tag where the card should appear. The card renders right before it:

```html
<script src="https://mcp.tc/w/audio-studio.js" async></script>
```

To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.

```html
<div data-mcptc="audio-studio"><a href="https://mcp.tc/i/audio-studio">Audio Studio on mcp.tc</a></div>
```

Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.

If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).

For a README or other Markdown docs, use the badge instead:

```markdown
[![Audio Studio on mcp.tc](https://mcp.tc/i/audio-studio/badge.svg)](https://mcp.tc/i/audio-studio)
```

Reference: https://mcp.tc/embed

Change history

This server runs on your computer, so we follow its PyPI package: each new version shows up here, with edits by its owner.

Follow Audio Studio and we’ll email you when something changes.

  1. , Automatic check

    New version 1.2.0 (was 1.1.1). Read from PyPI.

  2. , Automatic check

    Tracking started: version 1.1.1.

FAQ

Can I paste mcp.tc/i/audio-studio into my MCP client?

No. Audio Studio runs on your own computer, started by your client, so it has no web address to connect to. The quick link is the page to share; the install command is uvx --python 3.11 audio-studio-mcp --torch-backend cu126.

Does Audio Studio need an API key?

No. It doesn’t declare any keys or environment variables. It runs with your user account’s permissions, so check what its tools can reach.

Is Audio Studio a remote or a local server?

Local. Your client starts it as a process on your computer with uvx --python 3.11 audio-studio-mcp --torch-backend cu126, which needs uv (Python).

What can Audio Studio do?

You can generate background music, instrument loops and sound effects from a text prompt, produce 1 to 4 candidates per call and Re-style a clip, regenerate a time range or extend a track.

Which clients can use it?

Any client that starts local servers: Claude Code, Claude Desktop, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. claude.ai and ChatGPT only connect to remote servers.

Does mcp.tc track changes to Audio Studio?

Partly. It runs on your computer, so we follow its PyPI package: its History tab shows each new version and edits by its owner. Follow the listing to get an email when it changes.

Who wrote this page?

mcp.tc’s robot read Audio Studio’s public metadata (its package and repository pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.

mcp.tc isn’t affiliated with KanaWorks_AI. This page was built from Audio Studio’s public metadata, last checked on 16 Nov 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.