Extracted from canvas-website with:
- Web Speech API transcription (Chrome/Edge, fast)
- Local Whisper AI model (offline capable, ~75MB)
- PWA support with service worker
- Docker + Runtipi deployment configs
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
