In simple English
This tool helps researchers transcribe interview recordings and organize their notes in one private place. It turns spoken audio into text on your own computer, so sensitive conversations never leave your machine. You can review transcripts, assign speaker roles, create codes, and build research themes. It is free to use and runs locally, but requires some technical setup on your computer.
What it is
A self-hosted web application for qualitative research that runs either inside Docker (a way to run a program inside its own sealed box, so it cannot break anything else on your server) or directly through Python (a programming language). It handles local audio transcription, transcript review, theme development, and data export.
What it is good for
Solo researchers, qualitative analysts, and academic teams who need to transcribe sensitive interviews locally and want to avoid sending audio files to cloud-based transcription services.
- Keeps all interview audio and text strictly private on your own computer.
- Transcribes audio locally using Whisper without paid cloud API keys.
- Exports portable project archives for easy backup and sharing.
- Requires manual command-line setup and basic technical knowledge.
- Transcription can be slow when running on a standard CPU without a graphics card.
- Lacks user accounts or built-in access controls, so it is meant for single users or trusted networks.
manual interview transcription and cloud-based AI transcription services
ffmpeg
- openai/whisper111k stars
Provides the core speech recognition engine used for local audio transcription.
- snapcast/snapcast8.0k stars
A server and clients that play one audio stream in several rooms, kept in time with each other.
- MusicPlayerDaemon/MPD2.8k stars
A background music player with no interface of its own, controlled over a network by separate client programs.
- AcademySoftwareFoundation/OpenTimelineIO2.0k stars
An interchange format and library for editing timelines: the order and length of cuts, and references to the media, but not the media.
python -m venv .venv source .venv/bin/activate pip install -e ".[asr]" interview-analysis doctor interview-analysis serve