Feature Requests

Descript has so much potential to be an incredibly powerful tool, but the current focus on all the AI tool hype is really hurting the product. 95% of the time I try to use Underlord, it doesn't come close to a correct result, no matter how simple the request or how clear the prompt. Absolutely there are great use-cases (eye contact & auto multicam are examples that actually enhance my projects) and lots of great tools and improvements lately so I don't want to sound negative or anti-AI entirely, I'm not, but the focus lately on all marketing I've seen has been mainly generative tools that either aren't working that well or that I don't remotely need as a podcast producer (like generative video). What Descript needs most are UI and functionality improvements, not AI hype. There are countless suggestions in this community, many of which seem relatively simple to implement, that would improve the app far more than these AI tools. Just a few that come to mind now: organizing projects into folders strategizing app updates better (so it isn't constantly like "restart the app!!") further improving timeline UI so that layer height can be adjusted and vertical scrolling of layers is easier (a scroll bar, a way to control height of layer and audio bars, toggles for different types of layers like to be able to show or hide audio, etc) exporting audio from a video composition (used to be able to do it, why require another composition to be made? Then if you have to make an edit you have to do it in multiple compositions, unnecessary) exporting chapter markers (I use Buzzsprout and I've tried to submit this request over and over again) being able to adjust marker locations and scene boundaries by dragging in the timeline improving transcription accuracy improving assigning of speakers (very buggy often, always needs correcting) improving the sequence editor (very tricky to edit when there are multiple tracks) make audio editing more like a DAW to be able to control individual tracks (a bigger update but this should be a top priority since pro audio editing should be a core element of a podcast editor) returning to having actual humans respond to support requests, not AI bots I can't be the only user that wants to see my subscription fees put to these kind of things instead of towards AI tools that are highly unreliable and that I don't even need. And again, I say this as a fan and longtime user of Descript that sees so much more potential in it.

Being able to use a virtual camera a la OBS would allow for significantly more control of the video while doing screen recording. Currently there's no way to manipulate the video at all, such as rotating for a vertically oriented camera, color correction, brightness/contrast adjustments, etc.

Please actually name the different types of templates because there's no way to clearly request them from Underlord when 3 have the same name.

I'd like to have this done automatically when using the Descript recorder instead of having to do a bunch of work arounds to separate them.

Please give us the ability to adjust the layouts section. I have to scroll down everytime to choose a layout pack, get past the generic ones, go to private, then scroll all the way down to the newest one i made all because i cant customize there they go. Maybe a tab for favorites and the ability to remove ones we will never use.

In recent years, the need to digitize physical records has grown rapidly, creating a surge of interest in technologies that can seamlessly convert images of printed pages into editable content. Among these tools, document ocr software ( https://quickimagetotext.com/document-ocr ) has become a critical resource for professionals who handle large volumes of paperwork, enabling faster access to information and reducing manual entry errors. Its applications range from legal offices managing contracts to academic researchers archiving historical documents, reflecting a broad shift toward efficiency and digital organization. The software relies on advanced pattern recognition to identify characters accurately, even from low-quality scans or complex layouts. Beyond simple text recognition, modern systems integrate machine learning to improve accuracy over time, learning from corrections and adapting to varied fonts and languages. This evolution has allowed organizations to automate workflows that were once labor-intensive, such as data extraction for invoices, forms, or survey results. By reducing human error, institutions can maintain higher standards of compliance and documentation, ensuring that critical information is preserved without the risk of misinterpretation. The combination of speed, reliability, and adaptability has positioned OCR technology as a staple in digital transformation initiatives across multiple industries. As digital archiving becomes the norm, users increasingly expect seamless integration with other software platforms, allowing scanned content to flow directly into cloud storage or analytics systems. The focus has shifted from merely converting text to creating searchable, structured, and usable data that supports decision-making. Continuous improvements in accuracy and processing speed make it possible to handle massive datasets efficiently, while the reduction in manual labor frees up time for strategic tasks. Ultimately, the adoption of intelligent text recognition tools reflects a broader trend toward optimizing information management, bridging the gap between analog documents and digital intelligence, and empowering organizations to operate with both agility and precision.

Since you are moving towards more AI help in our workflow, in the future, if AI could suggest from all the available libraries the right B-Roll for the scenes we are active in, that would be amazing.

It seems that if I send a link to a specific composition to a NEW person for review, when they log in they are taken to the FIRST composition that was created in the project instead of the project I copied the link to. This may only happen for people who click the link and login to descript (tested using google login) for the first time, but is very confusing. This is not a problem when sending a 'Published' link to a project, but not all collaborative features are available in this mode.

I’ve been a loyal Descript customer for years, but since the new pricing structure was introduced, my monthly bill has skyrocketed from $30 to $195—despite no changes to my workflow. Frankly, this increase feels excessive. I can’t help but feel betrayed and taken advantage of. Over the years, I’ve recommended Descript to dozens of creators, but this new pricing model has left me no choice but to walk away. What once felt like an empowering tool for creators now feels like just another tech company exploiting its customers and showing them nothing but contempt. I’m genuinely disappointed and saddened by this experience.

I would like the ability to export individual scenes, clips, or selections from translation compositions (with translated subtitles or dubbed audio) in Descript. Currently, this is only possible for the original composition, but not for translated versions. This feature would greatly improve workflows for multi-language content and social media publishing. Thank you!