Trigger: video file uploaded to your S3 bucket


  1. Transcribe: uses speech recognition AI to turn the audio track into a JSON transcript

  2. Subtitle: take the ASR output and convert it to an SRT subtitle file

  3. Upload the video to Mux

  4. Upload the SRT to Mux as a subtitle sidecar file

  5. Webhook: sends the Mux URL for the aforementioned asset to embed in your application

Here's a video walkthrough on how you can create this flow in minutes:

Did this answer your question?