Descript

Descript is a video editor, audio editor, screen recorder, and transcription tool. It’s not a typical editor though, it’s different. You can edit your videos (or audio) by editing text. You can write, record, transcribe, edit, collaborate, and share your videos and podcasts with Descript. 

TL;DR: Descript is a video/audio editor that lets you edit like you would a doc.  It has a lot of cool features like AI voices (clone your own voice or use their stock voices), background removal, automatic transcription, one-click studio sound, one-click “um” and “uh” remover, and automatic subtitles you can customize with animation.  It’s a different experience for those who have used typical video editors.  But, once you get the hang of it, it’s quicker.  Go with the Pro tier, which gets you access to everything you need, and have fun!  

Some of the main features of Descript are:

 

Transcription: Transcribe audio and video files automatically. Descript has built-in transcription that transcribes your audio as you record it. if you’re recording within Descript. If you import audio or video with an audio track from your computer, Descript will transcribe it right after you import.

 

Editing: Edit audio and video files by editing text to trim, cut, rearrange, or correct video footage.

 

Overdub: Overdub is a standout feature of Descript. It allows you to create realistic voiceovers (using your own voice or one of Descript’s stock voices) or correct mistakes in your audio track using text-to-speech (TTS) technology. To use Overdub to correct mistakes in your voiceover or audio track, you create a custom Overdub voice by recording some training audio (or uploading a recording you already have.) Then, when you’re editing, just assign your Overdub voice to a speaker label and type in the text you want to generate as audio.

 

Studio Sound: Improve the sound quality of your recordings with noise reduction, leveling, and EQ. It’s really easy – just one click.

 

Filler word removal: Automatically remove filler words like “um” or “uh” from your recordings.

 

Background removal: powered by artificial intelligence, which means you don’t need a physical green screen to change your video background.

 

Subtitles & captions: Fancy subtitles are super-easy with customizable fonts, colors, and styles including live text that changes the color or background of each word as it’s spoken.

 

Publish & share: Export your files to various formats, upload directly to one of several platforms, or share them with collaborators online.

Overall Rating
4/5

PROS

  • Descript lets you edit audio and video by editing text, just like a document, and that magic makes editing much easier than a traditional video editor.  
  • Transcription is done in a click and fine-tuning the AI transcription is simple.  
  • Overdub is a really cool trick AND it also saves a ton of time fixing bloopers.  
  • Studio Sound makes crappy audio sound really good with a single button click and I’m still a bit surprised that it truly is that simple and it actually works. 
  • Filler word removal is a brilliant feature that makes producing polished audio or video so much easier.
  • AI background removal does a decent job of ditching everything in a video except the subject.  
  • Big, colorful, animated subtitles are not just popular right now, they’re expected.  Descript gives you the tools to easily generate subtitles in just about any color, size, shape, and movement you could imagine.
  • Descript offers an impressive list of platforms to publish to – directly from within the editor.  
  • Descript is constantly updating and improving.  
  • There are plenty of articles and videos on the Descript website ranging from getting started to troubleshooting topics.
  • Descript has an active Discord community where users can get help and inspiration and sometimes the Discord CEO is in there himself.  He also makes some of the how-to videos on the Descript website.

CONS

  • Editing video or audio like a doc is different.  If you are used to other video/audio editors, it will seem unnatural sometimes.  (stick with it)
  • Some things in the user interface are not intuitive.  That might be because I’m comparing the experience to a typical video editor.  Learning the names of things like sequences or compositions, and how they work, can be a little overwhelming.
  • Constant updates and improvements is a pro.  But, it also creates a con when tools and settings in the application get renamed or moved.  It’s all part of Descript’s effort to fine-tune and constantly improve.  Major releases aren’t annoyingly frequent and Descript always posts a list of changes and usually some videos to go along with it – you just have to read/watch them.
  • Some users report that they have submitted support tickets that have gone unanswered.  I have not had a need to contact support, since all of my issues have been answered by the documentation, videos, or Discord server.  So I cannot give any personal observations or quantifiable data on support response.

Pricing

Descript pricing comes in 3 general flavors: Free, Creator, and Pro.  There’s an Enterprise tier as well for large teams and organizations.

 

Free: The free tier gives you enough access and output to get familiar with Descript, try everything out, and see if it’s a good fit for you.  There are limits on transcription, resolution, and the stock library, among other things.  This tier might be OK for a one-time project or infrequent hobby projects.  One limit that is really critical is the 1000 word vocabulary for overdub.  What this means is that your overdubs will have some of the words in each sentence replaced with “Jibber” (or maybe it’s Gibber?)  So, you won’t get a ready-to-publish AI voiceover but, you’ll be able to test out the tool for your purpose and get a feel for whether it suits your needs.

 

Creator: The creator tier has the same 1,000 word vocabulary limit for overdub.  The limits for transcription hours and such are higher than the free plan, but still limited.  Like the free tier, the number of stock assets you have access too are limited, AI background removal and studio sound are limited as well.

 

Pro: The Pro tier made the most sense to me.  There’s a 30hr per month transcription limit – so that’s 30 hours of audio transcribed in Descript.  Other than that, most everything else is unlimited in the Pro tier.  Unlimited exports, unlimited overdub, unlimited studio sound, unlimited stock library access, etc.  The Pro tier also gets you filler word removal for not just um and uh, but 18 different filler words and repeated words.  

Descript Pricing

2 Responses

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.