Overdub Fixes Voiceover Mistakes in a Snap

I was editing a video about George Washington and discovered that I mistakenly said 1976 instead of 1776.  Oops!  Although I’m trying to be less of a perfectionist these days, a mistake of 200 years on a really important date just won’t fly.

 

Normally, the only way to fix this is to re-record myself saying 1776, cut the wrong part out of the video, and insert the new recording.  Not fun. Fortunately, I didn’t have to go through all that.  I just selected the text 1976 in the script panel of Descript, clicked Overdub, typed 1776, and a few seconds later Descript used it’s AI robots to replace my mistake with the correction… in MY voice. 

 

Descript is the editor that let’s you edit your video or podcast by editing text – like a Word document or a Google doc. One of it’s most impressive features is Overdub.

 

How does it work?  First, you provide training audio so Descript can figure out your voice.  You do this by either reading something into Descript using your microphone or uploading audio you already have.  Then, when you have a boo-boo like I did, you just select the word or phrase you want to replace, type the words you want instead, and the voice you want to use (in this case, your own voice) and then Descript will generate the audio in the selected voice.

What is overdub useful for?

  • Replacing an incorrect word or short phrase, like the example above.
  • Replacing a word or short phrase that came out unclear.  Is it just me?  I’ve been editing and found a word I just mumbled so badly it’s not even understandable.
  • Adding a word or short phrase that weren’t part of the original recording.

What it’s NOT good for?

  • Voicing your entire video or podcast.
  • Narrating an entire audiobook.
  • Replacing more than a few words or a short phrase to your production.
  • Adding more than a few words or a short phrase to your production.

Descript’s overdub feature is really good at replacing a word or two and usually it comes across seamlessly in the final production.  Overdub will usually replace a word or two before and after the word you want to replace, which usually puts the change in style at a natural break in the dialogue – rather than standing out as a single word that stands out.

 

However, if you use Overdub to add an entire paragraph of script you’ll notice that it doesn’t sound incredibly natural.  Yes, it will be your voice and you’ll recognize it as such.  But the pace and mood probably won’t come across as authentic. When I’ve tried to overdub an entire project or even a paragraph, it’s obvious to me that it’s an AI voice.  

 

Overdub is a great tool.  Just don’t expect it to do things it’s not good at (yet.)  

 

Leave a Reply

Your email address will not be published. Required fields are marked *

/SinglePost

Other creator tools you might like...

A Google Labs experiment, Whisk is an AI image generation platform that lets you use reference images for subject, scene, and style - whisk will try to capture the essence of those elements, but not the details.
AI Image, video and sound generation platform with editing and upscaling tools and AI-generated stock media.
Create, translate and personalize video at Hollywood standards with LipDub AI's proprietary AI lip sync video generator.
DreamFace's "Avatar Video" is a capable AI lip sync tool, when a source video of the subject (not a still image) is used. Popular for its ease of use and pricing.
Image & video generation platform based on models by Bytedance, with an AI lip sync tool that syncs mouth movements, facial expressions, and natural gestures
AI lip sync tool that animates a subject from a photo or video, syncing mouth movements to uploaded or generated audio. Adapts to the speaker’s vocal style for more expressive results.