Walkworth: Walk it. Say it. Keep it. A spoken trek journal on local open-source AI
Описание и применение
Walkworth позволяет записывать наблюдения во время похода голосом, хранить данные офлайн и автоматически генерировать проверенный журнал с цитатами, используя локальные модели и рабочий процесс Temporal.
Задача
Walkers need a way to record trek observations without interrupting their walk or relying on network connectivity.
Результат
Walkworth enables offline voice-based trek journaling with automatic transcription, extraction, and verified journal generation, eliminating the need for on-trail network or battery-intensive models.
Рабочий процесс
- Start a walk by tapping the big button, speak, tap again; phone buzzes to indicate listening and records GPS fix.
- Notes and photos are stored in IndexedDB and uploaded when network is available.
- On the laptop, whisper.cpp transcribes audio clips locally.
- Gemma 3 via Ollama extracts observations, captions photos, and writes journal lines, each line citing source note IDs.
- Temporal workflow orchestrates import, transcribe, align, extract, caption, compose steps with retries.
- FastAPI and SQLite store data locally; Render hosts the finished static journal.
- The journal is printed, published, or shared, with no fabricated content.
Доказательства
Walkworth is a trek journal you speak instead of type.
The phone buzzes when it starts and stops listening, so you never have to look at it.
A Temporal workflow transcribes (ElevenLabs Scribe), lines notes up with the GPX track, picks out what you saw, captions photos…
whisper.cpp (the small model) transcribes every clip. It copes with Hindi, Marathi and English in the same sentence, which is how I talk anyway.
- Дата записи: 2026-10-10T11:10:50.801Z