DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to share one warm audio server across all sessions with Audio Studio MCP

Run one local HTTP server so every MCP session uses the same loaded models.

  • Content
  • Advanced
  • 1 hour 15 minutes
  • From the README
  • Claude Code

Who it is forA developer who opens several client sessions a day and does not want the models to reload in each one.

The problemEach client session normally starts its own server process, so models load again for each session.

The outcomeOne local server on 127.0.0.1 that keeps the models warm and is reachable from every session.

What you need first

  • An Apple Silicon Mac (M1 or later) or a 64-bit Windows PC with an NVIDIA GPU (8 GB VRAM or more)
  • git and ffmpeg installed
  • About 6 GB of free disk on macOS or about 14 GB on Windows for the model and PyTorch
  • An MCP client such as Claude Code, Claude Desktop or Cursor
  • On Windows only: a free Hugging Face account with the Stable Audio 3 license accepted

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 for your agent

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 <path or description> 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.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page