Get Started

WhisperX

Fast speech-to-text with word-level timestamps and labels for who said what.

What you can do with it

  • Transcribe interviews with speaker labels
  • Make perfectly timed subtitles
  • Search hours of audio by word
Worth knowingFastest with an Nvidia GPU.

Getting started

We haven’t written a step-by-step guide for this one yet. Our free mission shows you how to install any tool from GitHub safely, so you can try it today.

Start the free mission