fieldmemo: keep the phone in your pocket, talk to it, get a field journal at home
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass AI disclosure: I built this with an AI coding agent, which wrote most of the code and the first draft of this post. I read it, watched the demo and approved the text. Everything below about what worked and what broke comes from the build log in the repo, not from memory. What I Built fieldmemo turns the voice…
This project, called fieldmemo, creates a field journal from voice memos recorded during outdoor walks, all without using the internet or a phone screen. To use it, record your thoughts and observations on a walk, then run a single command on the recorded memos and the GPS track from your device. fieldmemo will generate three files: a readable field journal (journal.md), a map layer (walk.geojson) with pins marking your locations, and a CSV file (notes.csv) for each sighting or issue.
The system uses Whisper for speech-to-text conversion, with some custom training to improve accuracy on countryside-specific terms like bird and mushroom names. It also uses Gemma 4, an open-weight AI model, to interpret the transcripts and create the journal, map, and CSV files. The demo version uses synthetic voice recordings and a made-up GPS track for testing purposes, but the code is designed to work with real-world data as well.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
