Skip to main content


ATransCribe is a speech-to-text service. It uses Whisper model for transcription. Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.Also using its underlying deep learning technology it process soundclips and removes background noises etc. for better results.The app is developed and used for the H2020 project AI-PROFICIENT.

atctranscribe logo