# Nomen Audio

- **Event:** [Built with Opus 4.6: a Claude Code hackathon](https://cerebralvalley.ai/e/claude-code-hackathon)
- **When:** Feb 10 at 12:00 PM – Feb 17 at 10:00 AM (EST)
- **Where:** Location TBA
- **Team:** [Peter Breslin](https://cerebralvalley.ai/u/astrobrez)
- **GitHub:** https://github.com/peterbreslin/nomen-audio
- **Demo video:** https://drive.google.com/file/d/1kI1W114RVc0jCwkBQtkG8ESFhublW_XN/view?usp=sharing
- **Gallery:** https://cerebralvalley.ai/e/claude-code-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/claude-code-hackathon/hackathon/gallery/227

Nomen Audio is a standalone windows program that intelligently generates filename and metadata information for professional (and otherwise) audio assets. The system reads all embedded metadata in an asset (iXML, BEXT, RIFF INFO chunks) and enables the user to edit them directly in-place and/or add addtional metadata fields. An ML pipeline that uses open source models (MS-CLAP zero-shot classification + ClapCap captioning) provides a first-pass suggestion for each file's metadata, adhering to industry conventions. Suggestions can be reviewed and adjusted individually, or accepted and saved in bulk across an entire batch. Nothing touches disk until the user explicitly saves. There's some additional features here and there. Everything runs completely offline.

---

Markdown version of https://cerebralvalley.ai/e/claude-code-hackathon/hackathon/gallery/227. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt