ABOUT THIS PROJECT
What is this?

This is a fully client-side audio transcription system built with Transformers.js, powered by Whisper Large V3 Turbo running directly in your browser using WebGPU. Your audio files are never uploaded to any server - everything is processed locally on your device for maximum privacy.

About the Creator

Rasmus Aagaard
Industrial PhD student at Laerdal Medical and the Technical University of Denmark (DTU).

My research focuses on model compression for efficient inference and on-device deployment of machine learning models. I'm passionate about making AI accessible and practical for real-world applications.

Connect with me on LinkedIn →

Support This Project

If you find this tool useful, consider buying me a coffee to support further development!

AUDIO TRANSCRIPTION SYSTEM v2.0
[ READY ]
🔒
Your audio never leaves your device

All transcription is done locally on your computer. Your audio files are processed entirely in your browser — nothing is uploaded to any server.

[ CLICK TO SELECT FILE ]
TIMESTAMP TRANSCRIPTION DATA
[ NO AUDIO FILE LOADED ]