Who it is forA video editor or game developer who has a generated track that is too short or the wrong style for a new cut.
The problemA 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 outcomeAn extended or re-styled track with candidates, followed by loudness normalization to the target level.
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
- Set up and register the server as described in the Quick start section of the README.
- Ask the client: "Extend this track to 90 seconds and normalize it to -16 LUFS."
- Ask the client to use edit_audio with continue for extension, variation for a full restyle, or inpaint to regenerate a time range.
- Ask the client to run process_audio on the chosen result to normalize loudness and export the final format.
- Compare the candidates by listening, then keep the one that fits your cut.
Prompt for your agent
Using the audio-studio MCP server from the audio-studio-mcp repo, call edit_audio with continue on <path to track> 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.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: 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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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