Reading the repo
Opening the box…
Reading the repo
Opening the box…
How to install on Windows
Utility for unpacking, organising, and transcribing a WhatsApp chat export
Saved setup from 11 h ago
Will it work on Windows?
Heads-upIt also needs 3 settings in .env (1 secret).
The maintainers included install.sh. Run it from the cloned folder after reading it.
bash install.sh
Then run powershell -ExecutionPolicy Bypass -File .\setup.ps1. It stops at the first error and is safe to run again. Servers and tests aren't started; it lists them at the end. Read it first.
Needs Git: winget install Git.Git
git clone https://github.com/danielrosehill/WhatsApp-Export-Unpacker.git cd WhatsApp-Export-Unpacker
Python >=3.10, FFmpeg
winget install Python.Python.3.13 winget install Gyan.FFmpeg
Fill in secrets: OPENAI_API_KEY
Copy-Item .env.example .env
python -m venv .venv .venv\Scripts\Activate.ps1 pip install -r requirements.txt
flask run
After running ./install.sh, launch the web interface:
./wa-unpack
Then open http://127.0.0.1:5000 in your browser.
Upload — Drag and drop your WhatsApp export ZIP file onto the upload zone (or click to browse). The zone features a WhatsApp-themed green gradient with visual feedback during upload.
Review Statistics — After upload, a statistics grid displays:
Configure Processing Options:
.opus audio to text via OpenAI Whisper (enabled by default)Anonymize Participants — A table displays each participant with their message count. For each:
Choose an Alias Style from the dropdown:
Process — Click "Process Export" to generate outputs. A progress bar shows processing status.
Results — View generated files with download buttons. If HTML was generated, an inline preview displays the chat viewer directly in the browser. Click "Process Another Export" to start over.
No reports for Windows yet.
GitManual AI Agent reads the 3 key files and writes a step-by-step guide for Windows. Once written, it's saved for everyone.