Ghost in the Machine: Keep Family Stories Alive with Local AI

Description and use

Ghost in the Machine is a local-first app that records, transcribes, and archives family stories using Whisper, keeping data on the user’s machine for privacy and independence.

Problem

Preserving family oral histories without relying on cloud AI services and ensuring privacy.

Outcome

The prototype demonstrates a fully local workflow for capturing, transcribing, and archiving family stories, eliminating cloud dependencies and preserving privacy.

Workflow

• Record or upload an audio file
• Transcribe speech using Whisper via faster‑whisper
• Review and edit the transcript
• Add title, date, and tags
• Save to JSON archive
• Search or export stories

Evidence

I built Ghost in the Machine, a local-first oral-history archive designed to help preserve family stories and memories before they are lost.

Source

The application lets users: 1.Record a story or upload an audio recording. 2.Transcribe speech using an open-weight Whisper model through faster-whisper.

Source

The speech model is loaded on the machine running the application. Its weights may need to be downloaded on first use; once cached, transcription can run locally without sending audio to a hosted AI API.

Source

Using an open-weight model and an inspectable codebase makes this project easier to study, adapt, and run independently.

Source