Can I vibecode Supernormal?

text
Build a personal replacement for Supernormal in an empty repository, focusing on bot-free capture and converting meetings into structured deliverables via custom templates.
Use Python 3.12, FastAPI, SQLite, whisper.cpp, and a polished HTMX + Tailwind CSS interface; do not offer alternative stacks.
The core job to be done: Record or import a meeting without an intrusive bot, transcribe it locally, identify speakers, and generate highly customized, context-aware notes and deliverables (e.g., project briefs, follow-up emails) based on personal templates.
Make the first run work locally with one documented command. Store all user data locally by default in SQLite.
Put secrets and optional LLM API keys in .env, ship .env.example, and never commit credentials.
Add explicit start, pause, resume, and stop controls with a visible recording indicator for bot-free browser audio capture. Support importing WAV, MP3, M4A, and MP4 files through ffmpeg.
Run transcription locally and display timestamped, editable segments. Let the user rename speakers and propagate corrections through the transcript.
Implement a "Template Engine": allow users to create and save custom markdown prompts (e.g., "Sales Discovery", "Weekly Standup", "Client Brief") that instruct an LLM on exactly how to format the summary and which specific deliverables to generate from the transcript.
Generate decisions, action items, questions, and the template-specific outputs from the approved text.
Export the final deliverables to Markdown, plain text, and WebVTT beside the original recording.
Include clear empty, loading, success, and recoverable error states. Add input validation, safe filenames, and graceful handling of unavailable APIs.
Write focused tests for the template formatting engine, core transcription loop, and one end-to-end happy path.
Create a README with setup, architecture, permissions, data location, and backup steps.
Do not add accounts, billing, telemetry, analytics, or a hosted control plane.
Deliberately leave out automated calendar bot attendance (Zoom/Meet integration), automatic cross-platform syncing (Slack/Notion API pushes), team sharing workspaces, and enterprise access controls.
Finish by running the tests and listing the exact commands used to run the app.