Voice Transcriptor

Windows desktop preprocessing foundation for long audio and video transcription jobs.

Setup and run

Install Python 3.12 or newer plus FFmpeg/FFprobe, ensure both executables are on PATH, then install dependencies and launch:

python -m pip install -r requirements.txt
python -m voice_transcriptor

The app accepts .m4a, .mp3, .wav, .mp4, .mov, .webm, and .mkv. It probes the source with FFprobe and streams it through FFmpeg into mono 24 kHz AAC-LC .m4a chunks at 64 kbps. Video audio is selected directly, with no large intermediate extraction file.

Chunking is duration-based, not tied to a presumed universal upload-size limit. Defaults are 15-minute chunks with 15 seconds of overlap. Change duration, overlap, and temporary-file retention under Settings → Advanced.

Each job writes an exact-timestamp JSON manifest in its job-specific temporary directory. Files are removed after completion, cancellation, or failure unless retention is enabled for debugging. Active preprocessing can be cancelled from the main window.

This milestone prepares media only. It does not call a transcription API or upload chunks.

Tests

python -m pytest -v
python -m compileall -q src tests

The OpenAI API key is stored through keyring rather than in the JSON settings file.