{"slug": "echonote-ai-i-built-an-offline-lecture-notes-app-for-my-friend", "title": "EchoNote AI: I Built an Offline Lecture Notes App for My Friend", "summary": "A developer built EchoNote AI, an offline lecture-notes app that runs Gemma 3 1B locally on a laptop CPU with no API keys and no internet dependency after setup. The app transcribes recordings, detects audio type to generate tailored summaries and exam questions, and stores notes in an AES-256 encrypted local database, with automatic GPU/CPU detection that falls back to CPU on machines with 4 GB of RAM. It was built for a friend, student Anshumita Ray, who records lectures and previously had to re-listen to hours of audio to write notes.", "body_md": "*This is a submission for the [Hacktoberfest Weekend Challenge: Build for a Friend](https://dev.to/challenges/hacktoberfest-weekend-2026-10-01)*\n\nI built **EchoNote AI** for my friend **Anshumita Ray**.\n\nAnshumita records her college professor's lecture on her phone during class. She does this because she cannot catch everything in real time. Sometimes a side conversation distracts her. Sometimes she forgets an important word, or misses a whole part of the lesson. Later, she has to listen to hours of audio again just to write her notes.\n\nEchoNote AI fixes this. She uploads her recording or records live in the browser. The app writes the full transcript, then makes a clean summary with key definitions and exam questions. If she forgot something, she can ask the AI a question about the lecture and get an answer based only on what the professor said.\n\nIt runs fully on a normal laptop. No API keys. No internet after setup. Her notes are stored in an encrypted local database on her own device.\n\n**100% Local CPU · No API Keys · AES-256 Encrypted · Offline-First**\n\n[**Watch Demo**](https://youtu.be/ylCl8rsBIuw) · [** Features**](https://github.com/codebysumit/echonote-ai#-features) · [** Setup**](https://github.com/codebysumit/echonote-ai#-installation) · **Deploy**\n\n**EchoNote AI** is a professional, Claude & NotebookLM-inspired **audio intelligence studio** that converts any recording into structured, encrypted notes — all running entirely on your own laptop CPU, with zero API keys and zero internet dependency after setup.\n\nDesigned for **college students, school kids, teachers, working professionals, recipe keepers, and voice note creators**.\n\n*Upload a lecture. EchoNote AI transcribes it, detects what it is, writes you a tailored summary with exam questions, and lets you chat with Gemma AI about its content — forever stored privately in your encrypted local database.*\n\nWatch EchoNote AI in action:\n\n| Feature | Details | \n|---|---|\n| ⚡ **Auto GPU / CPU Detection** | Automatically uses the best | \n\nEvery important part is open source:\n\nThe app checks the hardware when it starts. It uses an NVIDIA GPU or Apple Metal if they exist, and falls back to CPU on any laptop with 4 GB RAM. I picked the small 1B model on purpose, because a student laptop must be able to run it.\n\nIt also detects the type of audio. A college lecture gets exam questions. A meeting gets action items. A recipe gets ingredients and steps.\n\nHere is the thing. A closed API would have failed Anshumita in three ways.\n\nOpen weight models made all three possible. I chose a model small enough for her laptop, ran it myself, and changed how it writes notes for each type of audio. With a closed API I could not have done that for free.\n\n**Best Use of Gemma.** EchoNote AI runs Gemma 3 1B locally on CPU. It writes all summaries and exam questions, and it powers the chatbot that answers from the lecture transcript.", "url": "https://wpnews.pro/news/echonote-ai-i-built-an-offline-lecture-notes-app-for-my-friend", "canonical_source": "https://dev.to/codebysumit/echonote-ai-i-built-an-offline-lecture-notes-app-for-my-friend-8hn", "published_at": "2026-10-04 06:01:54+00:00", "updated_at": "2026-10-04 06:07:54.122946+00:00", "lang": "en", "topics": ["ai-tools", "large-language-models", "generative-ai", "ai-products", "developer-tools"], "entities": ["EchoNote AI", "Anshumita Ray", "Gemma 3 1B", "GitHub", "Hacktoberfest"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/echonote-ai-i-built-an-offline-lecture-notes-app-for-my-friend", "markdown": "https://wpnews.pro/news/echonote-ai-i-built-an-offline-lecture-notes-app-for-my-friend.md", "text": "https://wpnews.pro/news/echonote-ai-i-built-an-offline-lecture-notes-app-for-my-friend.txt", "jsonld": "https://wpnews.pro/news/echonote-ai-i-built-an-offline-lecture-notes-app-for-my-friend.jsonld"}}