Feature Requests

I'd love to be able to do interviews with people who don't speak the same languange as me via live translation during recording.

Project: Cathy Hockey Multi Cam Video (project ID 7e92d24b-454a-4bb0-bd07-49b1caba3624) Setup: Descript desktop app on Mac, working alongside the Descript project agent / API, which operates on the cloud copy of the project. The problem: There is no way to see whether the desktop app has finished syncing to the cloud, and no way to force or confirm a sync. When every edit happens in one app this is invisible, but the moment the project agent is involved it becomes a real hazard: the agent edits the cloud copy, so any agent job fired while desktop changes are still uploading runs against a stale composition. The workflow guidance ends up being "wait and hope," because the app exposes no sync state at all. What this cost us in practice, on one episode: Manual setup done in the desktop app (sequence build, track fader changes, speaker labels) wasn't verifiably in the cloud before agent jobs ran — the only available check was comparing composition durations by eye between the desktop timeline and an API read. At one point the cloud copy reported the composition at 2:47:38 (duplicate sequence insertions) while we were troubleshooting in the desktop app — with no way to tell whether we were looking at a synced state, a mid-sync state, or divergence, and no timestamp anywhere saying "cloud last updated at X." Track volume changes made in the desktop app appeared not to take effect in cloud reads for an extended period — impossible to distinguish "not synced yet" from "changed the wrong control" (both turned out to be true at different points, and diagnosing which was which took hours). Suggested fixes: A visible sync indicator in the desktop app — synced / syncing / offline, with a "last synced to cloud" timestamp on the project. A manual "Sync now" action. On the agent/API side: expose the project's last-synced timestamp, and have the project agent warn (or refuse) when the cloud copy it's about to edit is older than the most recent desktop session — an "editing a possibly stale composition" guard. Longer term: a conflict/divergence warning when desktop and cloud states differ materially (e.g. composition duration mismatch). For a workflow where a human edits in the app and an agent edits via the cloud — which your project agent actively encourages — sync state can't stay invisible.

Subject: Silent composition — nested track volume controls are undiscoverable, and one accepts changes it doesn't persist Project: Cathy Hockey Multi Cam Video (project ID 7e92d24b-454a-4bb0-bd07-49b1caba3624) Setup: Multicam workflow — a sequence built from one master audio file plus four camera clips (camera audio used for sync only), the sequence placed on a composition's script track. Desktop app on Mac, synced to cloud. The problem: My composition played back completely silent, and it took the better part of a morning to find out why. The cause: the same audio track effectively has three separate volume controls at different levels — (1) the track inside the sequence in the media library, (2) the composition's own copy of that sequence sub-track, and (3) the parent script track in the composition. I set the volume to 100% at levels 1 and 3, in the places the UI naturally led me, and stayed silent — because level 2, the one that actually governs playback, was at 0% and is the hardest of the three to reach. Nothing in the UI indicates that a child track is silencing playback while the visible parent shows 100%. Steps to reproduce: Create a sequence from a master audio file + multiple camera clips; set track volumes inside the sequence. Add the sequence to a composition. In the composition, set the sequence sub-track volumes to 0 (e.g. while muting camera scratch audio). Open the sequence from the media library and set its master audio track to 100% — playback of the composition remains silent. Select the composition's script track — the properties panel shows Audio 100%, while the composition still plays silent. A second, related bug (API/agent): The Descript project agent's track-modification tooling, when asked to set gain on a composition's sequence sub-track, reports success but the change does not persist — re-querying the document shows the gain reverted to 0. If sub-track gain isn't writable in that context, the operation should fail loudly instead of silently reverting. Suggested fixes: When a composition's effective output is silent because a child track is at 0, surface that on the parent — e.g. a muted-speaker badge on the script track and on the waveform, with a click-through to the offending layer. Consolidate or clearly label the volume hierarchy — "this control affects the library sequence only, not compositions that already contain it." Make the agent/API modify_track gain operation on sequence sub-tracks either work or return an explicit error, never a false success.

Great creative tools often improve because people keep sharing practical suggestions. sales coaching for sdrs https://lemcoach.com/for-sdrs fits into a broader conversation about how communities exchange ideas that make workflows more effective. Every feature request starts with someone noticing a small friction in their daily routine. Those observations may seem minor at first, but they often lead to meaningful improvements. A collaborative feedback space allows different perspectives to meet in one place. Users can explain real situations instead of only reporting problems. Others can support ideas they find valuable through discussion and voting. This creates a clearer picture of what matters most across the community. Creative work is constantly changing with new technologies and expectations. Listening to users helps products adapt to those changing needs over time. Open conversations also encourage thoughtful problem-solving instead of quick assumptions. Many practical features begin as simple suggestions from everyday users. Seeing how others approach similar challenges can inspire new ways of working. Constructive feedback benefits both creators and the wider community. It helps identify patterns that may otherwise go unnoticed. Small improvements can make everyday tasks smoother and more enjoyable. Communities grow stronger when ideas are shared respectfully. Every contribution adds another perspective to the discussion. Innovation often comes from continuous learning rather than dramatic changes. A space that welcomes feedback encourages steady progress. Meaningful discussions help shape tools that better serve real users. Simple suggestions can have a lasting impact over time. Thoughtful collaboration remains one of the strongest drivers of improvement. That is why community-driven feedback continues to be valuable for everyone involved.

While exploring account executive sales coaching https://lemcoach.com/for-aes it becomes clear how valuable structured feedback can be for product improvement. Ideas become more useful when they are supported by clear context instead of quick reactions. A well-organized discussion helps teams understand the real challenges behind each request. Community voting also highlights which improvements matter to the largest number of users. Thoughtful feature suggestions often reveal everyday workflows that deserve more attention. Constructive comments can provide examples that make requests easier to evaluate. Sharing practical experiences encourages more informed conversations among contributors. When updates are communicated openly, users feel connected to the development process. Transparency creates confidence that feedback is being reviewed with purpose. Different perspectives often uncover creative solutions that might otherwise be overlooked. Clear descriptions reduce confusion and help avoid duplicate suggestions. Respectful discussions make collaboration more productive for everyone involved. Tracking progress on requested features gives users better visibility into future changes. Organized feedback platforms make it easier to prioritize improvements based on real needs. Every contribution, no matter how small, can help shape a better experience. Listening carefully is often the first step toward meaningful innovation. A community grows stronger when ideas are shared with clarity and patience. Good feedback is not only about identifying problems but also about explaining why they matter. Consistent participation creates a valuable record of evolving user expectations. The best discussions focus on solving challenges rather than assigning blame. Simple, actionable suggestions are often the easiest for teams to evaluate. Over time, collaborative feedback helps products evolve in ways that reflect genuine user experiences. Open communication benefits both contributors and the teams building the product. Small insights shared today can become meaningful improvements in future releases.

Descript now supports transcription in 23 languages, but Overdub only works in English. This feature would bring Overdub support to more languages

I do not know how to program an AI transcription engine, and that is all I utilize Descript for. First of all, I must add that I have tried other engines available, and only one gets close enough to the performance you all provide - yet, the complexity, required training, required hardware/software, and expense is relatively unreasonable compared to what you offer. The only feature they offer is a comprehensive (yet hard to train) editing tool, which with care, experience, and lots of customization, I have nearly replicated just with MS Word. On the positive side, which is all I have today (though I will try to come up with something to request...), whatever the Descript team has done to the transcription engine lately is SUPERB. It is so good that I have to go to my editing macros and readjust them, because the usual corrections they seek no longer exist. Surprisingly, I see phrases being quoted, and in a 600-page document, with maybe 50 quoted phrases and sentences provided by the AI, only about seven of them were misquoted - and it was mostly because the speakers broke the sentence in ways that the AI could not reconcile. I was surprised and delighted - I did not think this was possible. Additionally, names of weird places that I usually have to hazard a guess on a search engine are easily found and properly spelled by Descript a lot better than before. As what I transcribe is legal, I found even case law properly transcribed - a new one for any AI I have worked with; it is not all-encompassing and nowhere near all correct, but positively surprising nonetheless. This is where the AI gets it wrong or not at all: days and years. For some reason, twenty twenty six does not translate as 2026; one May twenty four does not translate as 1 May 24; et cetera. I have macros for it, but thought you would like to know. That one seems easier to fix at a glance than proper quotations! There are many other numerical issues related to translation, but dates seem like the more standardized I can think of that would benefit the most people. I have also noticed positive differences in the capitalization used by Descript; it catches things that I occasionally forget to capitalize. Military acronyms are getting better formatted as well, which is a very huge surprise... (if you all need military court transcripts and examples, I could get you sanitized versions for your AI dictionary and learning model, as well as lists of weird terms and how they are spoken - I used to teach this material). So, good feedback thus far, and thanks for all the work you all do. Oh, I remember trying out the feature that will replace certain things in the translated text for whatever we gave it... I have no idea if it has been worked on since I stopped using it, but when I tried it (only when it first came out), I immediately saw the value in it but that it needed lots of work. I do not know if you all do beta testing of features with enterprising users that can give you detailed feedback to help you, but I volunteer as long as time allows. :-) Thank you all for the work you do. Thanks to Descript, my productivity is at least 250% more AND better than before using this AI tool, which allows me to work fewer hours for the same productivity, or increase my product (but being a 100% disabled vet that needs constant breaks, I need tools that help me increase hourly productivity, since working more hours is occasionally impossible due to health./physical issues). Again, thanks!! ( I would NOT MIND military discount, even if only on the annual pricing... just saying... LoL)

In my own and experienced opinion I do not think that we have an RTL issue here seems to me that if we are for example using the vanilla JavaScript GSAP animation we just need to reverse the direction of start of the animation, it has been rectified in that library so we need to rethink that same implementation and solution for the functionality to work correct.

When I'm recording audio narration, I don't want it to hide the video. Sometimes I'm reading from or describing the video. When I hit record the video turns into a huge soundwave which is far less useful. Then when I exit recording, my timeline has reverted to default settings and I have to resize everything again.

When the edit is done on the podcast, I need to a limiter with compression to get the correct output format. Loudness - 16 LUFS and top level -1 dB. That can be automated when exporting. You have normalization as a function but that is not enough. Today I have to use another DAW to do that quite standardized function.