Feature Requests

Whenever the Underlord gives me an answer, I want to start reading this answer right away, without waiting until the answer is completely finished. But currently I'm not able to do this, because when the Underlord appends text to the bottom, the entire paragraph of text moves up, which makes it not readable. Usually when this happens on any other web-based chat application, I'm able to scroll up a little bit so that expanding the page to the bottom doesn't change the position of the paragraph that is being appended to. But in Descript application, whenever I do this, it forces to scroll to the bottom and the paragraph just moves, making it unreadable.

After editing just one video all my monthly credits are gone. This is insane. Can you please either adjust credit price by x10 or revise how you account for their usage.

The Underload feauture should be able to keep a history of prompts that were inputed in the past, so that when users come back to the project, they remember where they left off

Automatic camera versus screen share switching on multi-track with Underlord based off of mouse and computer screen activity Basically, I want the Underlord to be able to tell when I'm moving my mouse, when I'm clicking stuff on screen, all that sort of stuff on my screen share. If I'm not moving my mouse and not clicking my screen, it'll go back to my full face camera, where it shows my full face, so the editors can add animations, stuff like that. If I'm doing stuff on my screen, it goes back to screen share.

It just doesn't work. Please stop trying to make fetch happen. Please build useful tools for video editing, not a terrible AI layer that can't do anything.

My eyes are jumping all over, particulary one eye. This file is in Coaching Lectures, inside is Mod 1 and Mod 2 for example.

It is great to have the built-in features to generate ai images and video within the tool, and be able to select in settings which AI to use (we use nano banana and veo primarily). However, when generating you either have to select from some preset styles, or copy-paste in your own brand guideline prompts each time in addition to the instructions to get images based on your brand image/video generation style. (I realise you can also upload a image that can influence style, but that is not how we define brand so would be very different to using nano/veo outside descript) It would be great to be able to add custom styles where you can enter the definitions/prompts to be reused each time, and ideally be managed like templates/brand such that you could choose which styles are available/are default for team (e.g. we'd probably want to be able to select between 2-3 styles for types of images, videos, have one be the default, and be able to select none if doing an entirely custom prompt.

Please make AI credits budget visible when you're in a project, not having to go to Usage to see my credits. I know you start showing them when you're running out, but you should always show them so we have a better idea of what we're using. It's a new feature and I don't want to have to constantly be doing math to understand how many credits I'm using.

Right now if your content is for example in spanish, most features dont work and also the recomended titles and descriptions still are all in english

Current Pain: We follow a consistent editing pattern across almost all projects: Certain types of cuts Certain caption style Certain framing and motion choices Right now we have to recreate those decisions every time, or hunt through settings and properties. Impact: Slower onboarding of editors. Increased risk of inconsistent look and feel across content. Requests / Ideas: Project-Level Defaults A “Project Style” or “Global Settings” section where we can define: Default aspect ratio Default fonts/colors Default caption style Default behavior for cuts, motion, zooms Quick Design and other automation should respect these settings. Workflow Presets Ability to say: For this workspace, all videos should by default: - Use Style A - Use Layout Set B - Avoid certain transitions (e.g., no jumpy zooms)