Can I vibecode MinutesLink?

text
Build a deliberately narrow personal substitute for MinutesLink, focusing on extreme simplicity and effortless meeting documentation.
Use exactly this stack: Python 3.12 + FastAPI + whisper.cpp + SQLite, with a clean and minimal React frontend.
Primary job: Build a private, dead-simple meeting notes pipeline. A user uploads an audio file (or records directly in browser), and the app automatically transcribes it with speaker identification, generates a concise meeting summary, and extracts clear, assignable action items.
Start from an empty folder and create the complete working project. Make the default mode single-user and private.
Store user data locally in SQLite. Do not add analytics, telemetry, ads, or third-party accounts. Emphasize a "privacy-first" local architecture.
Put every secret and external credential in .env and provide .env.example. Use an LLM API (key in .env) for the summary and action item extraction.
Design the UI to require zero technical setup: just a drag-and-drop zone for audio files, a progress indicator, and a beautiful dashboard showing the final Summary and Action Items side-by-side with the transcript.
Implement a searchable archive page where users can find past meetings by keyword or date.
Include clear empty, loading, validation, success, and failure states. Add Markdown export so the user can easily copy notes into their preferred text editor.
Use accessible keyboard navigation, labels, focus states, and sensible contrast. Validate untrusted input and never log secrets or private file contents.
Deliberately exclude these paid-product advantages: automated calendar integration (bots that automatically join Zoom/Meet), real-time streaming transcription, team collaboration/commenting features, and complex CRM integrations.
Do not fake integrations, network effects, proprietary data, model quality, compliance, or security claims.
Where an external API is optional, keep the app useful without it and explain the degraded mode.
Write focused unit tests for the data model, transcription parsing, and action item extraction logic. Add one end-to-end smoke test that proves the core loop works.
Create a README with setup, permissions, architecture, data location, backup, and limitations.
Add scripts for install, development, test, build, and a production-style local run.
Run the tests and build before finishing, then fix errors rather than merely describing them.