# Kazuumi

- **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:** [Kazuumi Nishimura](https://cerebralvalley.ai/u/kazuumi)
- **GitHub:** https://github.com/KazuumiN/voice-trunk
- **Demo video:** https://youtu.be/MKlE5C4OPHc
- **Gallery:** https://cerebralvalley.ai/e/claude-code-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/claude-code-hackathon/hackathon/gallery/128

VoiceTrunk eliminates the busywork of documenting in-person workshops. Instead of manually managing dozens of recorders and files, simply plug in a device: VoiceTrunk handles ingestion, deduplication, and uploading instantly.

The AI pipeline then goes beyond simple transcription. It performs Claim Extraction, classifying every factual statement by stance (affirmation, concern, quote). VoiceTrunk turns chaotic raw audio into structured, searchable civic knowledge, letting teams focus on listening rather than file management.

---
[IMPORTANT NOTE] Honestly, this project is currently incomplete and not fully operational...

---

Markdown version of https://cerebralvalley.ai/e/claude-code-hackathon/hackathon/gallery/128. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt