# AI use cases for Audio Studio MCP (kanaworksai-hue/audio-studio-mcp) Repo: [kanaworksai-hue/audio-studio-mcp](https://github.com/kanaworksai-hue/audio-studio-mcp) | Use cases: 4 | Page: https://dedupedai.com/use-cases/kanaworksai-hue-audio-studio-mcp/ Audio Studio MCP is a local MCP server that generates background music, instrument loops and sound effects with Stable Audio 3, then loops, normalizes and exports them, with no cloud service or API key. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Generate a seamless BGM loop for a game scene: https://dedupedai.com/use-cases/kanaworksai-hue-audio-studio-mcp/generate-game-bgm-loop/ - Create a sound effect and export it for Godot: https://dedupedai.com/use-cases/kanaworksai-hue-audio-studio-mcp/create-sound-effects-for-godot/ - Extend or restyle an existing track with edit_audio: https://dedupedai.com/use-cases/kanaworksai-hue-audio-studio-mcp/extend-or-restyle-existing-track/ - Share one warm audio server across all sessions: https://dedupedai.com/use-cases/kanaworksai-hue-audio-studio-mcp/share-one-audio-server-across-sessions/ ## How to generate a seamless BGM loop for a game scene with Audio Studio MCP Repo: [kanaworksai-hue/audio-studio-mcp](https://github.com/kanaworksai-hue/audio-studio-mcp) | Difficulty: Intermediate | Time: 1 hour 15 minutes | Basis: From the README Describe a scene in one sentence and get candidate music loops sized for game BGM. **Who it is for:** An indie game developer or hobby game maker who needs a looping background track for a level, menu or cafe scene and has no budget for a composer. **The problem:** Finding or commissioning a looping BGM track that matches a mood, tempo and length takes time and money. **The outcome:** Three candidate BGM WAV files, each with a JSON sidecar, processed into a seamless loop at -16 LUFS and exported as OGG. ### Steps 1. Run `git clone https://github.com/kanaworksai-hue/audio-studio-mcp.git` and then `cd audio-studio-mcp`. 2. Run `brew install ffmpeg` if ffmpeg is not installed, then run `./install.sh`. 3. Run `claude mcp add --scope user audio-studio -- /path/to/audio-studio-mcp/.venv/bin/audio-studio-mcp` to register the server. 4. Ask the client: "Make a 60-second lo-fi BGM loop at 85 BPM for a cafe scene, give me 3 candidates." 5. Ask the client to run process_audio with a seamless loop and loudness normalization to -16 LUFS, exporting OGG, then listen to the candidates and keep the best one. ### Prompt to paste into your agent ```text Using the audio-studio MCP server from the audio-studio-mcp repo, call generate_audio for a 60-second lo-fi BGM loop at 85 BPM for a cafe scene with variations set to 3. Then call process_audio on the chosen file to make a seamless loop, normalize to -16 LUFS and export OGG. Verify that the output file exists in outputs/ with a matching .json sidecar. ``` ### Caveat The first generation on macOS may download the medium model (about 5.9 GB), so the first run is much slower than later ones. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/kanaworksai-hue-audio-studio-mcp/generate-game-bgm-loop/ ## How to create a sound effect and export it for Godot with Audio Studio MCP Repo: [kanaworksai-hue/audio-studio-mcp](https://github.com/kanaworksai-hue/audio-studio-mcp) | Difficulty: Intermediate | Time: 1 hour 15 minutes | Basis: From the README Describe a sound by its source, action, material and space, then export it as OGG. **Who it is for:** A game developer using Godot who needs a specific sound effect, such as a door slam, and does not have a sound library that covers it. **The problem:** Generic sound libraries rarely match the exact object, material and room a scene needs. **The outcome:** A short sound effect file that matches the described source and space, peak normalized and exported as OGG for Godot. ### Steps 1. Set up the server with `./install.sh` on macOS or `powershell -ExecutionPolicy Bypass -File install.ps1` on Windows, then register it with `claude mcp add --scope user audio-studio -- /path/to/audio-studio-mcp/.venv/bin/audio-studio-mcp`. 2. Ask the client: "I need a heavy wooden door slamming in a stone hallway. Export it as OGG for Godot." 3. Check that the request uses the sfx type and fills the sound_source, sound_action, sound_material and sound_space fields, so the output is not generated as music. 4. Ask the client to run process_audio with peak normalization and OGG export. 5. Import the OGG file from outputs/ into your Godot project and test it in the scene. ### Prompt to paste into your agent ```text Using the audio-studio MCP server from the audio-studio-mcp repo, call generate_audio with audio_type sfx for a heavy wooden door slamming in a stone hallway, filling sound_source, sound_action, sound_material and sound_space. Then call process_audio with peak normalization and OGG output. Verify that the OGG file is in outputs/ and that its .json sidecar lists the sfx settings. ``` ### Caveat The README warns that without the SFX prefix, sound effects often come out as music, so the sfx type and sound fields matter for good results. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/kanaworksai-hue-audio-studio-mcp/create-sound-effects-for-godot/ ## How to extend or restyle an existing track with edit_audio with Audio Studio MCP Repo: [kanaworksai-hue/audio-studio-mcp](https://github.com/kanaworksai-hue/audio-studio-mcp) | Difficulty: Intermediate | Time: 1 hour 15 minutes | Basis: From the README Lengthen a generated track, change its style, or regenerate one section. **Who it is for:** A video editor or game developer who has a generated track that is too short or the wrong style for a new cut. **The problem:** A track that fits most of a scene often needs more length or a different feel, and re-creating it from scratch loses what already works. **The outcome:** An extended or re-styled track with candidates, followed by loudness normalization to the target level. ### Steps 1. Set up and register the server as described in the Quick start section of the README. 2. Ask the client: "Extend this track to 90 seconds and normalize it to -16 LUFS." 3. Ask the client to use edit_audio with continue for extension, variation for a full restyle, or inpaint to regenerate a time range. 4. Ask the client to run process_audio on the chosen result to normalize loudness and export the final format. 5. Compare the candidates by listening, then keep the one that fits your cut. ### Prompt to paste into your agent ```text Using the audio-studio MCP server from the audio-studio-mcp repo, call edit_audio with continue on to extend it to 90 seconds, with 2 candidates. Then call process_audio to normalize the chosen file to -16 LUFS. Verify that the output is about 90 seconds long and that its .json sidecar keeps the source generation info. ``` ### Caveat The README's sample for extension shows a 20-second track extended to 40 seconds, and it does not state a maximum length for edits beyond the model limits listed in the configuration section. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/kanaworksai-hue-audio-studio-mcp/extend-or-restyle-existing-track/ ## How to share one warm audio server across all sessions with Audio Studio MCP Repo: [kanaworksai-hue/audio-studio-mcp](https://github.com/kanaworksai-hue/audio-studio-mcp) | Difficulty: Advanced | Time: 1 hour 15 minutes | Basis: From the README Run one local HTTP server so every MCP session uses the same loaded models. **Who it is for:** A developer who opens several client sessions a day and does not want the models to reload in each one. **The problem:** Each client session normally starts its own server process, so models load again for each session. **The outcome:** One local server on 127.0.0.1 that keeps the models warm and is reachable from every session. ### Steps 1. Run `./install.sh` on macOS or `powershell -ExecutionPolicy Bypass -File install.ps1` on Windows to finish setup. 2. Run `.venv/bin/audio-studio-mcp --http 8765 --preload` on macOS, or `.venv\Scripts\audio-studio-mcp.exe --http 8765 --preload` on Windows, and keep it running. 3. Run `claude mcp add --scope user --transport http audio-studio http://127.0.0.1:8765/mcp` to point Claude Code at the server. 4. Open a new session and ask for a short sound effect to confirm the server responds. ### Prompt to paste into your agent ```text Using the audio-studio-mcp repo, start the server with `.venv/bin/audio-studio-mcp --http 8765 --preload` and register it with `claude mcp add --scope user --transport http audio-studio http://127.0.0.1:8765/mcp`. Then call generate_audio for a 3-second sound effect at to verify the server responds, and check that a file appears in outputs/. ``` ### Caveat The HTTP server must stay running in a terminal, and the README describes it only as listening on 127.0.0.1, so it is not meant for access from other machines. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/kanaworksai-hue-audio-studio-mcp/share-one-audio-server-across-sessions/