# Build brief — a focused alternative to Granola

> **Verdict:** Yes, for personal use · **Buildability:** 81/100 · **Category:** Meeting Notes
> **Source:** https://www.canitbevibecoded.com/granola
> Independent editorial assessment from Can It Be Vibe Coded? Not affiliated with, endorsed by, or derived from Granola. Verify current pricing and capabilities before acting.

## Context

**Granola** — AI meeting notepad that turns transcripts into structured notes. It currently costs $14/mo.

A local recorder plus Whisper transcription plus an LLM note template covers the core personal loop. The paid product is mainly polish, meeting context, sync, and team workflow.

This brief describes a focused, single-operator replacement for the part of Granola that is genuinely reproducible. It is deliberately narrower than the product it replaces, and it says so in writing. Build the useful core; do not pretend to have rebuilt the rest.

## What you are building

Record system/mic audio, transcribe with Whisper or a hosted speech API, send transcript plus your rough notes to an LLM, save Markdown notes by date and meeting title.

- Capture supplied audio, transcribe it, create structured notes, and export them.
- A responsive interface with real empty, loading, success, and error states.

## Requirements

### Functional

- MacOS or Windows audio capture library.
- Local folder or SQLite database.

### Data and integrations

- OpenAI/Anthropic API key or local Whisper model.

Each of these needs a real account, credential, or quota. Set them up before writing feature code.

### Non-functional

- Accessibility: semantic markup, labelled controls, visible focus, and reduced-motion support.
- Security: server-side secrets, validated input, and no credentials in the client bundle.
- Reliability: retries with backoff on external calls, and a clear failure state when a provider is down.
- Portability: the operator can export their data and leave without losing it.

## Implementation brief

Build me a local meeting-notes app like Granola for macOS. Requirements:

- A menu bar app (Swift or an Electron tray app · pick the simpler to ship) with
  Start/Stop Recording. Record system audio + mic (use whatever screen-audio capture
  permission approach is standard).
- On stop: transcribe the audio locally with whisper.cpp (medium model), or via
  OpenAI/Groq Whisper API if a key is present in .env.
- Send the transcript to an LLM (key from .env) with a prompt that produces: a
  5-bullet summary, decisions made, and action items with owners.
- Save to ~/MeetingNotes/YYYY-MM-DD-HHMM.md: summary at top, full transcript below
  a divider. Keep the audio file next to it.
- No accounts, no cloud storage, no telemetry. Everything stays on my machine except
  the API calls, and work fully offline if whisper.cpp + a local model are available.
- Include a README with the permissions I need to grant and how to install deps.

## Delivery standard

- Inspect the repository first, then write a short implementation plan before writing code.
- Deliver the smallest complete end-to-end workflow first; every primary control must work against persisted data.
- Use real validation and storage; never substitute fake dashboards, decorative controls, hard-coded success states, or mock integrations.
- Include responsive layouts plus genuine empty, loading, success, validation, and failure states.
- Keep secrets server-side in environment variables, provide .env.example, and never commit credentials or user data.
- Add structured logs around every external call and return actionable errors without leaking sensitive details.
- Write unit tests for the core logic and one automated test of the main user journey.
- Finish with a README covering setup, architecture, data location, backups, tests, deployment, and known limitations.

## Acceptance criteria

- [ ] A clean install starts the app using only the README and .env.example.
- [ ] The primary journey works from first visit through saved result, reload, edit, export, and deletion where applicable.
- [ ] Invalid input, missing configuration, provider failure, and an empty database each have a usable state.
- [ ] The interface works at 390px and 1440px, is keyboard navigable, and shows visible focus on every control.
- [ ] Tests, type checking, linting, and a production build all pass with no ignored failures.
- [ ] No part of the interface implies a live integration, security guarantee, or scale capability that was not actually built and verified.

## Non-goals

Do not build these, and do not claim to have replaced them:

- Sync across devices.
- The mobile app.
- Automatic calendar joins.
- Someone else's servers & support.
- The last 20 percent is sync, migration fidelity, speed, and edge cases.
- Connectors, OAuth flows, and vendor API changes require constant upkeep.

## What you still own after launch

- Secure credentials, rotate secrets, and handle provider rate limits.
- Run migrations, backups, restores, and dependency updates.
- Test the critical journey after every model, API, or hosting change.
- Monitor failures and fix the edge cases a first prompt will miss.
- Maintain every third-party integration as APIs and OAuth rules change.

## Risk

**Operational risk.** The code is achievable; dependable data, integrations, and ongoing operations are the real cost.

Editorial confidence in this assessment: medium. No independent one-shot implementation is linked yet.

## Prior art

Working open-source software you can read, fork, or borrow from before starting:

- [quill](https://github.com/dremnik/quill) — open-source Granola alternative
- [whisper.cpp](https://github.com/ggml-org/whisper.cpp) — local transcription engine

---

Generated by [Can It Be Vibe Coded?](https://www.canitbevibecoded.com) · Full report: https://www.canitbevibecoded.com/granola