VoxBuddy
What I Built I built my friend a voice-note assistant that keeps their audio on their laptop My friend has a habit I think a lot of us have: they record voice notes whenever something comes to mind, then almost never come back to them. assignments. People to call. Things to buy. Meetings. Random details they know they will forget. So for this Hacktoberfest weekend, I built VoxBuddy — a small…
Prathamesh2007-o7 developed an application called VoxBuddy for Hacktoberfest weekend. The app aims to turn voice notes, which people record for various purposes, into actionable tasks and summaries. VoxBuddy achieves this by keeping all AI processing local on the user's machine rather than sending the recordings to a cloud AI API.
When a user records or uploads a voice note through VoxBuddy's browser interface, the audio is sent to a Flask backend server. The backend utilizes Whisper, a local AI model, to transcribe the speech into text. This transcript is then sent to Qwen3, another local AI model available through Ollama, which processes the text to generate a structured summary, actionable tasks, priorities, and deadlines.
The application features an HTML, CSS, and JavaScript frontend, while Python and Flask power the backend. Once the user's laptop has the necessary models and dependencies installed, the entire application can run locally. This local-first approach is significant because it addresses privacy concerns, ensures offline functionality, eliminates per-request API costs, and allows for greater flexibility in model selection and customization.
Unlike a general-purpose chatbot, VoxBuddy is tailored to a specific user's habit of recording voice notes. By processing the data locally, the app ensures that any personal or sensitive information within the voice notes remains secure, as it doesn't leave the user's machine.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
