audio-studio-mcp

本页保存的是公开项目资料快照，阅读过程不需要连接 GitHub。

 A KanaWorks_AI project

English | 简体中文 | 日本語

🎧 Listen to samples · Quick start · Tools · FAQ · ⭐ Star

Audio Studio MCP gives Claude Code, Claude Desktop, Cursor and any other MCP client a sound studio that runs on your own Mac or Windows PC. Ask for background music or a sound effect in plain language; the model generates it locally with Stable Audio 3. Then it can loop it, normalize the loudness and export it for your game engine or video editor. There is no cloud service and no API key, and generating doesn’t cost anything.

A real session, shortened. Claude picked a loop length of exactly 11 bars so the beat stays in time when it repeats.

✨ Highlights

GenerateBGM, instrument loops and sound effects from one sentence, 1–4 candidates per call EditRe-style a whole clip, regenerate a time range, or extend a track FinishSeamless loops, fades, loudness (LUFS), 48 kHz WAV / OGG / FLAC LocalRuns on Apple Silicon (MLX) or an NVIDIA GPU (PyTorch). Nothing is uploaded

• Reproducible: every file gets a .json sidecar with its prompt, seed and settings.
• Prompting built in: the server teaches the client the official Stable Audio 3 prompt format, so a request like “make it sound like a creaky door” becomes a prompt the model understands.
• Same output as upstream: on a Mac, results for the same seed are bit-for-bit identical to the official sa3 CLI. On Windows it calls the official Stable Audio 3 PyTorch API.

🎧 Hear it

All of these were generated by this server on an M1 Mac and were not edited by hand. Open the sample page →

	Sample	Prompt
	Lo-fi cafemusic · 30 s · 85 BPM	Lo-fi hip-hop chill track with mellow electric piano, soft vinyl crackle, low-pass filtered drums…
	Epic orchestralmusic · 30 s	Epic cinematic orchestral trailer music with thundering taiko drums, soaring French horns…
	Chiptune adventuremusic · 20 s · 150 BPM	Upbeat 8-bit chiptune adventure theme with a bright square wave lead…
	Glass shattersfx · 3 s	source: glass bottle · action: shattering on impact · material: thick green glass · space: concrete floor
	Rain & thundersfx · 12 s	source: heavy rain and distant thunder · space: outdoor forest at night, wide stereo
	Synthwave, extendededit · 20 s → 40 s	edit_audio continue: a 20-second track extended to 40 seconds

MP3s are in docs/samples/, with prompts and seeds in samples.json.

🧭 How it works

flowchart LR
    U["You“make a cozy cafe BGM”"] --> C["Claude Code · DesktopCursor · any MCP client"]
    C -- "MCP" --> S["audio-studio-mcpgenerate · edit · process"]
    S --> M["Stable Audio 3MLX on Apple SiliconPyTorch on NVIDIA GPUs"]
    M --> F["WAV / OGG / FLAC + .jsonready for game & video"]

🚀 Quick start

macOS (Apple Silicon)

Requirements:

• Apple Silicon Mac (M1 or later), 16 GB RAM recommended
• About 6 GB of disk for the model
• git and ffmpeg (brew install ffmpeg)

git clone https://github.com/kanaworksai-hue/audio-studio-mcp.git
cd audio-studio-mcp
./install.sh

The installer sets up uv if needed, clones the official Stable Audio 3 runtime into vendor/ at a tested commit, creates .venv/, and downloads the medium model (1.4B, ~5.9 GB) from Hugging Face. It finishes by printing the exact command to register the server:

claude mcp add --scope user audio-studio -- /path/to/audio-studio-mcp/.venv/bin/audio-studio-mcp

Windows (NVIDIA GPU)

Requirements:

• 64-bit Windows 10 or 11 with an NVIDIA GPU (8 GB of VRAM or more) and a current driver. Tested on an RTX 3060 12 GB
• About 14 GB of disk for the model and PyTorch
• git (winget install Git.Git) and ffmpeg (winget install Gyan.FFmpeg)
• A free Hugging Face account. The PyTorch weights are gated: open stabilityai/stable-audio-3-medium and accept the license once

git clone https://github.com/kanaworksai-hue/audio-studio-mcp.git
cd audio-studio-mcp
powershell -ExecutionPolicy Bypass -File install.ps1

The installer does the same steps as on macOS, but installs PyTorch with CUDA and downloads the official PyTorch checkpoint of the medium model (~10.4 GB). If you aren’t logged in to Hugging Face yet, it asks for an access token with read permission (create one here). It finishes by printing the command to register the server:

claude mcp add --scope user audio-studio -- "C:\path\to\audio-studio-mcp\.venv\Scripts\audio-studio-mcp.exe"

Flash Attention is not needed. Without it, the runtime falls back to PyTorch’s built-in attention.

Claude Desktop, Cursor and other clients

Add this to claude_desktop_config.json, .cursor/mcp.json or your client’s MCP config:

{
  "mcpServers": {
    "audio-studio": {
      "command": "/path/to/audio-studio-mcp/.venv/bin/audio-studio-mcp"
    }
  }
}

On Windows the command is C:\\path\\to\\audio-studio-mcp\\.venv\\Scripts\\audio-studio-mcp.exe (backslashes doubled in JSON).

Installer options

macOS	Windows	Effect
--model all	-Model all	Also download the small, fast sm-music and sm-sfx models (+2.6 GB on macOS, +7 GB on Windows)
--skip-weights	-SkipWeights	Don’t download now; the first generation downloads them
-y	-Yes	Install uv without asking

On macOS, downloads are anonymous; logging in with hf auth login raises Hugging Face’s rate limit. On Windows, the PyTorch weights are gated: accept the license on each model page you download (medium, small-music, small-sfx) and log in.

[!TIP] Let your agent install it. Paste this into Claude Code: “Install https://github.com/kanaworksai-hue/audio-studio-mcp by following its README, then register it as an MCP server.”

Then just ask:

• “Make a 60-second lo-fi BGM loop at 85 BPM for a cafe scene, give me 3 candidates.”
• “I need a heavy wooden door slamming in a stone hallway. Export it as OGG for Godot.”
• “Extend this track to 90 seconds and normalize it to −16 LUFS.”

🧰 Tools

Tool	What it does
generate_audio	Text to BGM, instrument loop/stem or sound effect. 1–4 candidates per call, bpm, structured SFX fields
edit_audio	variation (re-style the whole clip), inpaint (regenerate a time range), continue (extend). 1–4 candidates
process_audio	Trim → trim silence → mono → resample / loudness → seamless loop → fades → peak normalize or ceiling → WAV / OGG / FLAC. Never modifies the input
unload_models	Free the model memory right away

Parameter notes

• audio_type: music / instrument / sfx / raw. The server adds the prefix the model was trained with (TrackType: Music, VocalType: Instrumental, …). Without the SFX prefix, sound effects often come out as music.
• variations: 1–4 candidates with seeds seed, seed+1, …. Use seed: -1 or leave it out for a random seed.
• sound_source / sound_action / sound_material / sound_space: describe a sound effect by what makes it, how it evolves, its texture and the space it is in.
• peak_ceiling_db (default −1): a safety ceiling. Louder peaks are turned down and quieter audio is never boosted. Use process_audio to normalize.
• process_audio normalization: peak is common for SFX. loudness normalizes to a target LUFS: −14 for streaming/video, −16 for game BGM, −23 for broadcast.

Generated files are 44.1 kHz 24-bit stereo WAV, written to outputs/ in this folder. Each one has a .json next to it. Processed files keep the original generation info under source.

⚙️ Configuration

Environment variables

Variable	Default	Meaning
AUDIO_STUDIO_OUTPUT_DIR	/outputs	Where audio files are written
AUDIO_STUDIO_IDLE_UNLOAD_MIN	10	Free the models after this many idle minutes (0 = never)
AUDIO_STUDIO_SA3_MODEL	medium	medium (best quality, up to 380 s), sm-music or sm-sfx (small and fast, up to 120 s)
AUDIO_STUDIO_MLX_CACHE_GB	1	macOS: cap on MLX’s buffer cache. Without it, a long generation can leave ~6 GB cached
AUDIO_STUDIO_DEVICE	cuda if available	Windows/Linux: PyTorch device, e.g. cuda, cuda:1 or cpu
AUDIO_STUDIO_SA3_DIR	/vendor/stable-audio-3	Use another stable-audio-3 checkout
AUDIO_STUDIO_BACKEND	auto	auto, sa3-mlx (Apple Silicon) or sa3-torch (PyTorch, NVIDIA)
AUDIO_STUDIO_FFMPEG	ffmpeg on PATH	Path to ffmpeg

Pass them with claude mcp add ... -e NAME=value or in the env block of your client config.

Share one server between sessions

Each client session normally starts its own server process. Models load on the first call and are freed after the idle timeout. To keep one warm process for every session, run it as a local HTTP server. It only listens on 127.0.0.1.

.venv/bin/audio-studio-mcp --http 8765 --preload
claude mcp add --scope user --transport http audio-studio http://127.0.0.1:8765/mcp

On Windows, start it with .venv\Scripts\audio-studio-mcp.exe --http 8765 --preload.

⚡ Performance

Medium model on an M1 Mac with 16 GB:

Task	Time
Two 3 s sound effects, cold start	~13 s
20 s of music, warm	~10 s (2× real time)
Continue to 35 s, incl. loading the encoder	~27 s
15 s of music with sm-music, warm	~1 s

Medium model on Windows with an RTX 3060 12 GB:

Task	Time
Two 3 s sound effects, cold start (incl. ~20 s model load)	~25 s
20 s of music, warm	~1.3 s
Continue to 30 s, warm	~2.2 s
380 s of music (the maximum), warm	~15 s
15 s of music with sm-music, warm	~0.7 s

On a Mac, loaded models use about 5–7 GB of memory. On the RTX 3060, the medium model peaked at about 5.3 GB of VRAM. Models are freed after the idle timeout or by unload_models.

📝 Prompting tips

From the official Stable Audio 3 prompt guide

1. English, 1–2 sentences, up to ~45 words. Avoid vocal words such as vocals, singer or lyrics.
2. Music: genre + adjectives → lead instruments → supporting layers → drums/rhythm → mood. Put the tempo in bpm.

   Lo-fi hip-hop chill track with mellow electric piano, soft vinyl crackle, low-pass filtered drums and soft plucked bass for a relaxed, dreamy vibe.

3. Sound effects: fill in source, action, material and space.

   source: glass bottle / action: shattering on impact, fragments scattering / material: thick green glass, sharp bright transient / space: concrete floor, close-up, dry

4. Match the length to the content: impacts 1–3 s, actions 3–6 s, ambience 6–15 s+, loops 6–20 s, full tracks 120–300 s (max 380 s).
5. Timing instructions like “climax at 15 s” are not followed reliably. Generate first, then use inpaint or continue.
6. The defaults steps=8 and cfg=1.0 are the official settings. For stricter prompt adherence, or to use negative_prompt, try cfg 3–7 (about 2× slower).
7. Results vary a lot by seed. Ask for 2–4 variations and pick the best.

The full guide is also sent to the client as the server’s instructions.

❓ FAQ

Does it run on Windows, Linux or Intel Macs?

Windows: yes, with an NVIDIA GPU. See Quick start.

Linux: with an NVIDIA GPU it uses the same PyTorch backend and should work, but it is untested and has no installer yet. Clone the upstream runtime into vendor/stable-audio-3 at the commit pinned in install.sh, then run uv sync --extra cuda and hf auth login.

Intel Macs and AMD GPUs are not supported.

Can it make songs with vocals?

No. Stable Audio 3 generates instrumental music and sound effects. It cannot produce intelligible singing or lyrics.

Can I use the generated audio commercially?

The code here is MIT. The model weights are under the Stability AI Community License, which sets the terms for the model and what it generates. Read it before commercial use. At the time of writing it allows commercial use for individuals and organizations with less than US$1M in total annual revenue.

Will an 8 GB Mac work?

It hasn’t been tested. The medium model needs about 5–7 GB while loaded, so 16 GB is recommended. The small sm-music / sm-sfx models are lighter.

My loop clicks at the seam.

Use WAV or OGG for loops. MP3 adds padding at the start and end, so it can’t loop seamlessly. Also try a longer loop_crossfade_ms, or ask the model to cut on a bar line.

🗺️ Roadmap

• Apple Silicon backend (Stable Audio 3, MLX)
• Windows backend for NVIDIA GPUs (Stable Audio 3, PyTorch)
• LoRA support (the upstream runtime already has it)

Issues and pull requests are welcome.

⭐ Like it? Star it

If Audio Studio made a sound you ended up using, please click ⭐ Star at the top of the repository page. It’s free, takes one second, and helps more than it looks:

• More people find it. Stars make the project easier to discover on GitHub, so more game developers and video makers get to use it.
• It keeps updates coming. Every star tells me someone finds this useful. That’s what keeps me working on the next update, like LoRA support.

Other ways to help: open an issue for a bug or an idea, or share a sound you made on X and tag @KanaWorks_AI.

🛠️ Development

uv run pytest                              # offline tests, no model needed
.venv/bin/python scripts/smoke_test.py     # end-to-end with the real model (~30 s on an M1)

On Windows: .venv\Scripts\python scripts\smoke_test.py (~45 s on an RTX 3060, including model loading).

src/audio_studio_mcp/
  server.py            MCP tools (backend-independent)
  prompts.py           prompt building and the instructions sent to clients
  post.py              post-processing and export
  backends/base.py     backend interface
  backends/sa3_mlx.py  Stable Audio 3 on Apple Silicon (MLX)
  backends/sa3_torch.py  Stable Audio 3 on NVIDIA GPUs (PyTorch)

A new platform is added as another backend in backends/.

📄 License and credits

• This project: MIT.
• Stable Audio 3 runtime: downloaded into vendor/ at install time. It is © Stability AI and MIT-licensed.
• Model weights: licensed under the Stability AI Community License. They are downloaded from Hugging Face (macOS: stable-audio-3-optimized; Windows: stable-audio-3-medium and the small models), not distributed here.
• Brand: the KanaWorks_AI name, logo and the Kana character are © 東京AI映像合同会社 (Tokyo AI Visuals LLC) and are not covered by the MIT license. See docs/brand.
• Built on: Stable Audio 3, MLX, PyTorch and the Model Context Protocol.

This is an independent project. It is not affiliated with or endorsed by Stability AI, Apple, NVIDIA or Anthropic.

Made with ♥ by KanaWorks_AI

If Audio Studio saves you time, a ⭐ keeps the updates coming and helps others find it. More projects: github.com/kanaworksai-hue