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.

Button to add current frame as context. Example image:

Improve the timeline interface of the video editor. Refer to processing tools from other software and integrate them into the editor, such as Trim Start and Trim End. There should be a default option to automatically detach audio when importing footage/video into the timeline (instead of having to manually disable it each time). Add the ability to customize the height of layers for better visibility; the current interface becomes very hard to read when multiple layers are stacked. Remove unnecessary or cluttered notifications when importing any video/footage into the timeline, or move them to other positions so they don’t obstruct the video preview. In addition to the existing layer lock feature, add an option to lock all layers simultaneously within a segment. Currently, locking everything requires clicking each layer individually, which is quite time-consuming. The feature for detecting segments to cut (from the in-point) in the original video is too slow and needs to be made faster. Add a feature that allows reverse lookup from a footage clip back to its original source video in the Project folder.

Apply your own LUTs to visuals in Descript.

The results of using a saved/trained speaker voice, and then in the editor being able to assign an image to produce an animated avatar works well. However, it appears you always have to add the avatar image as an option in a project, and the "AI Speakers" pane doesn't let you create or edit speakers to be able to add an image. It would be great in the "AI Speakers" pane you could create/edit the speakers, and that include assignment of the avatar image. It would also be natural to allow multiple images per ai speaker so you could have the avatar in a number of different scenarios/clothes etc with same voice.

I love the new Drive Folders feature but there isn't the option to NOT share a particular Drive Folder with the entire team. This renders the feature unusable for many of my files.

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.

Background: I'm a video editor transitioning from Premiere Pro to Descript. I produce both podcast-style interviews and short-form scripted theatrical content, both requiring multicam editing with 3+ camera angles plus separate audio tracks. Current Problem: When using create_sequence to combine multiple synced camera files, the automatic sync often fails. When this happens, there are no manual tools to correct the sync, making multicam workflows impossible without pre-syncing in external NLEs. Specific Issues: No Manual Sync Adjustment When automatic sync fails, there's no way to manually adjust individual track offsets Cannot drag tracks in timeline to align them (unlike Premiere Pro) No numeric offset input fields No Sync Refinement Tools Cannot see waveform comparison between tracks No visual feedback on sync confidence/quality No "re-analyze sync" button to retry with different parameters Sequence Workflow Limitations Individual tracks within a sequence aren't accessible for timing adjustments Cannot temporarily view/solo individual angles for sync verification Playback triggers all tracks simultaneously, making manual sync impossible Missing Sync Point Detection Should detect clapperboard audio spikes automatically Should allow manual marking of sync points (like Premiere's "Mark Clip" feature) Requested Features: Priority 1: Manual Sync Controls Ability to adjust individual track start offsets (in frames or seconds) Visual waveform overlay for comparing audio tracks Numeric input fields for precise offset adjustment Ability to drag tracks horizontally in timeline for visual alignment Priority 2: Improved Automatic Sync Sync confidence indicator (percentage or quality score) Option to retry sync with different sensitivity settings Automatic detection of clapperboard/slate audio spikes Manual sync point marking (user clicks sync frame on each clip) Priority 3: Better Sequence Workflow Ability to expand/collapse sequence to see individual tracks Solo/mute individual tracks within sequence for verification Scrub playback without auto-playing all tracks Visual indicators showing which tracks are in/out of sync Use Cases This Would Enable: Scripted Content: Multi-camera theatrical scenes with separate audio recorder (common in indie film production) Podcast Interviews: Multiple camera angles with dedicated audio interface Live Events: Concert footage, panel discussions, conferences with multiple cameras Educational Content: Instructor + screen capture + close-up camera Why This Matters: Descript's text-based editing is revolutionary, but multicam sync is a fundamental video editing capability. Every professional NLE (Premiere, Resolve, Final Cut, even free tools like Resolve) has robust multicam sync tools. Without these features, Descript cannot be used for professional multicam workflows, forcing users to: Pre-sync in external NLEs (defeating Descript's "all-in-one" value proposition) Abandon Descript for multicam projects entirely Adding these features would make Descript viable for a much broader range of professional video production, not just podcast editing. Technical Feasibility: These features already exist in other NLEs and are technically straightforward: Waveform analysis algorithms are mature technology Manual offset adjustment is basic timeline functionality Visual waveform comparison is standard in audio editing tools Business Impact: This would unlock Descript for: Film/video production professionals Corporate video teams Educational content creators Live event videographers Anyone shooting multicam content

just say I don't know

It needs "eyes" for edits that are already baked into uploaded videos. Right now, Underlord is essentially blind to any cuts or edits already present in the source footage. If the AI could use actual video awareness to analyze the video frames themselves, it would "see" existing edits and be infinitely better able to improve them, and add time remapping, visual improvements like color balancing, and transitions.