Nostalgia Cookbook

Description and use

The app lets seniors digitize recipes from voice memos into structured digital archives while keeping data private.

Problem

Grandparents preserve recipes only in memory or disjointed voice memos, making digital archiving difficult.

Outcome

The app enables grandparents to digitize recipes while preserving privacy, with structured data extraction and long‑form audio handling.

Workflow

• Upload or record audio in the app
• Gemini API transcribes audio to raw text
• Local Gemma 2 model extracts recipe structure from transcript
• Structured recipe and narrative are stored in MongoDB Atlas
• User can view and manage archived recipes

Evidence

I built the Nostalgia Cookbook, a privacy‑first web application designed specifically for my grandparent, who loves cooking but only preserves recipes in their head or via lengthy, disjointed voice memos.

Source

The application transcribes the audio and uses a hybrid AI system to separate the recipe (ingredients, metric/imperial measurements, structured steps) from the invaluable personal stories, historical context, and anecdotes woven into the recording.

Source

The application is built using a modern Next.js (App Router) frontend and backend architecture containerized with Docker, backed by MongoDB Atlas for data persistence.

Source

The raw audio file is initially parsed using the Gemini API (gemini-2.5-flash) via the @google/genai SDK to produce a raw, verbatim stream of consciousness text block from the voice recording.

Source

This unedited text transcript is then piped locally into Gemma 2 (9B) running on an open-source inference runner (Ollama).

Source