Feature Requests

I would like to request that Descript have an Auto-trim feature for audio and video, that allows us to remove long silences or pauses from the entire audio track, so basically cut out the silent parts and bring words closer together. Because I find that most of my work is moving words closer to each other to avoid the many pauses in my audio (some short pauses and some really long, so have to move the words a long way). The only software I've found that has such a feature is Reaper, here's a video to show you what I mean: https://www.youtube.com/watch?v=5OFYaL6pW3U&t=312s

Without a proper teleprompter it's difficult to speak while looking INTO the camera, and it looks fake when you see someone read a script while on their webcam. An AI tool to make the eyes of the person constantly look into the camera even when they are reading some text down on the screen would be awesome.

Folders in the Drive/Project view please to organize projects.

Would be helpful to easily select multiple clips at one time (without selecting the whole composition) in order to auto level volume etc which is currently only available on a clip by clip basis.

I would love to see your text/speech/video editing capabilities combined with an AI Avatar like the avatars at https://www.synthesia.io . Seems like a really powerful combination that would save me a ton of time.

Can you translate and create dubbing in different language?

Will you get Mandarin, Arabic (Modern), Brazilian Portuguese, Hebrew, Indonesian, Swahili, Ukranian, Russian, Persian, Spanish (Mexican)? And if you are going to add these languages, how soon?

There are words and names of companies that I use frequently in podcasts. I would love the ability to "teach" the transcription engine to recognize words, names, or phrases. Example: I host a podcast called the Modern Financial Advisor Podcast by Truelytics. Your transcription tool translated that to "modern angel adviser podcast by true Linux"

I want to be able to record a video with my own speak and voice, and then replace it with a stock voice. So when recording a tutorial video it's easier to speak it your self during the recording. But I would be great if I could that change my voice to a stock voice with a click of a button

Would be great to gave speaker voice generated for multiple languages.