Generate audio and sync lips to correct recording (VideoDub)

« To Transcriptions: Overview

VideoDub lets you effortlessly fix mistakes in your recordings without re-recording. Using AI, it automatically adjusts both the audio and lip movements to match your corrected text, making it look and sound like you said it perfectly the first time.

Videodub.gif
Step by step

  1. Log in to your Riverside account.
  2. Open a recording in the editor.
  3. In the transcript, select the word you want to correct.
  4. Click VideoDub.
    To apply VideoDub to a guest track, you must accept a legal disclaimer acknowledging that you have permission to do so.
  5. Type in the replacement text.
  6. Click Generate
    VideoDub generation may take a few moments, but you can continue editing while you wait.
  7. To revert a VideoDub correction, click the dubbed word in the transcript, then click Revert.
    Revert VideoDub

Icon.svg Good to know

  • Currently, VideoDub is only available in English.

  • VideoDub cannot be applied during the first 3 seconds of a recording.
  • You can apply VideoDub to up to two words at a time. If two words are selected, they will be replaced with a single dubbed word. However, you cannot replace a single word with two separate words.

  • Full sentence dubbing isn’t supported at this time.

  • Results may vary. AI accuracy depends on factors like pronunciation, lighting, and speaker positioning. For best results, keep your face clearly visible and avoid covering your mouth with your hands, a microphone, or other objects.

Learn more