Changelog

Follow up on the latest improvements and updates.

RSS

We’ve launched a ton of new ways to generate video and images in Descript over the last few months, and we’re hosting a live demo to walk you through all the best stuff, and even better, how to use it to level up your content with generated B-roll, animating images, and so much more.
Join CEO Laura and the team for a live demonstration of Descript's generative video capabilities on
October 28 at 1pm ET / 10am PT
.
The demo will cover how to use generate video features in your editing workflow, including:
  • Creating B-roll and supplementary content
  • Adding text animations
  • Changing camera angles
  • Working with animated clips
The session will include a Q&A segment where you can ask questions about the features.
Top ups—add more resources when you need them
image
Why top up?
For Creator and Business subscribers on our new plan types, top ups allow you to purchase additional media hours or AI credits when you're approaching your monthly limits. Now you can handle those busy production periods without changing your subscription plan.
image
You can find the new top ups by opening the Settings menu → Plan section, and clicking
“Add top ups.”
Media Hours:
  • 5 hours for $25 ($5/hour)
  • 20 hours for $80 ($4/hour)
  • 50 hours for $150 ($3/hour)
AI Credits:
  • 350 credits for $35 ($0.10/credit)
  • 1,000 credits for $80 ($0.08/credit)
  • 4,000 credits for $200 ($0.05/credit)
Top ups are purchased at the drive level (not per seat) and unused top ups expire after 12 months. When you use resources, Descript will automatically deduct from your monthly quota first before using your top ups. You can learn all about top ups on our Help Center.
Import files from other projects (beta)
We’ve added the ability to import files from other projects directly from the Project panel in the Editor. This is a great way to transfer files that you use frequently without having to re-process them, skipping the need to use Media minutes (or transcription hours if you’re on a Legacy plan.)
You can access you full library of files from within any project, allowing you to find files and quickly locate that perfect clip, intro, B-roll, or sound effect you've used before.
No more downloading and re-uploading files or burning extra media or transcription minutes – simply find and reuse what you already have.
This is our first step toward comprehensive drive media and search functionality, with more improvements coming in future updates. We'd love to hear your feedback on how this feature enhances your editing workflow.
Improved copy & paste behavior
We’re updating the way that copy and paste works in relation to Scenes and Scene boundaries.
  • When copying audio, vector, or media content and pasting with a playhead in the timeline, we’ll respect the playhead position, rather than snapping to a Scene boundary.
This update makes copy and paste behavior more intuitive by respecting where you've placed your playhead or what you've selected in the timeline. The new behavior gives you more precise control over where pasted content appears.
Don't worry, it's still easy to paste content at scene boundaries, as the playhead will automatically snap when approaching scene edges in the timeline.
Cancel and restart buttons added to Editor and Screen recorder
It’s finally here, a long request feature for our recorders: You can now Cancel or Restart recordings, giving you more control over your workflow and making it easier to start over when you need to. This feature is available for both the editor recorder, and the screen recorder.
What's New
  • Cancel button
    : Quickly discard your current recording if you want to start fresh without saving the current take.
image
  • Restart button
    : Instantly stop your current recording and immediately begin a new take with the same settings.
image
You can change your mind and resume from the confirmation panel with both cancel and restart options.
This highly requested feature helps streamline your recording process and ensures you can quickly recover from mistakes without disrupting your creative flow.
Model picker is now available from the AI tools panel
Model picker in panel
For users on our new plan types, we’ve added the model picker button directly to the AI tools panel when you select either Generate video, or Generate an image.
When using image or video generation in Descript, you'll now see a Cube icon that allows you to select different AI models for your generation tasks. This gives you the flexibility to choose the model that best suits your specific needs.
Different models offer different strengths:
  • Choose faster models when you need quick results
  • Choose cheaper models when you need to experiment
  • Select higher quality models when visual fidelity is paramount
  • Pick the right balance between speed, quality, and resource usage based on your project needs
The model picker puts more control in your hands. If you’re still on a Legacy plan, you’ll eventually be moved to a new plan type, or you can switch early to take advantage of the model picker, and our new top ups.
Bug Fixes
  • Fixed a bug causing “Can’t separate audio” error when using Avatar generation
  • Fixed a bug where toggling Studio Sound off/on deducts credits each time
  • Fixed an issue causing Underlord to provide inaccurate information about credit charges
  • Fixed a bug causing Spanish dubbing to stall
  • Fixed a bug causing a recording to fail to save
  • Fixed a bug causing recordings to be truncated
  • Fixed a bug causing editor recording cut short with “Instant playback duration was shorter than expected” error
  • Fixed a bug causing empty recording files in Rooms
  • Fixed a bug causing guest track (video/audio) missing from Rooms recording
  • Fixed a bug causing Rooms to fail to process video streams correctly
  • Fixed a bug causing Rooms to stop recording unexpectedly
  • Fixed a bug causing AI Speech preview to hang indefinitely
  • Fixed a bug causing layout and caption desync when editing overdub content
  • Fixed a bug causing Studio Sound to fail to apply after dubbing
  • Fixed a bug causing incorrect timing when exporting dubbed compositions
  • Fixed a bug causing cloned avatars to fail generation
  • Fixed a bug causing partial export of dubbed projects
  • Fixed a bug causing duplicated subtitles after translation
  • Fixed a bug causing Underlord to ignore remove commands in Agent flow
Introducing new plans and usage tracking in Descript
We're changing how we track usage in Descript, which means we're updating our subscription plans. As of yesterday, Free users have been onboarded to these updated plans, while existing paid users will stay on their current plans for now.
Note: None of these changes affect Enterprise users, so feel free to skip ahead to the rest of the Changelog if you are on an Enterprise plan.
What's changing for Free users
Your Descript Free plan now includes:
  • 60 media minutes per month
    — These track media files uploaded to or recorded in Descript, regardless of whether they're transcribed. Transcription time is no longer tracked.
  • 100 lifetime AI credits
    — These replace AI uses and track usage of AI features like Studio Sound, Green Screen, Eye Contact, and AI-generated media and avatars.
We've also expanded your access to AI-powered editing in Descript, including:
  • Underlord
    — Let our AI co-editor handle the tedious parts of editing for you.
  • Generate images
    — Create bespoke, custom images from a text prompt.
For paid subscribers
If you're a paid subscriber, your current plan and pricing remain unchanged for now. Later this year, all plans except those on enterprise will be updated to include media minutes and AI credits, with at least 30 days notice before any changes occur. In most cases, this transition will not impact the price you pay.
You also have the option to switch to our new plans immediately to take advantage of media minutes and AI credits, including access to exclusive features like the latest generative video models.
Questions?
For more details about these changes, including a full breakdown of what's included in all plans, check out our comprehensive FAQ in the Help Center.
New media generation model selection in Settings
Settings - Gen Media Models
For users on the new plan types, we’ve added new premium, supercharged generative model options to the settings menu.
These models offer higher quality output, delivering significantly improved quality, particularly with video models like
Veo3
, and image models like
Nano Banana
. They can also provide better character consistency across image generations, maintaining appearance and identity across different angles and scenes.
Image generation models
The following image generation models are available:
  • Flux Kontext [Pro]
    - Default model for image generation
  • Flux [Dev]
    - Alternative image generation model
  • GPT Image 1
    - OpenAI's image generation model
  • Nano Banana (Gemini Flash Image)
    - Google's Gemini-based image model
  • Qwen Image
    - Good for editing details and text in images
Video generation models
The following video generation models are available:
  • Pixverse 4.5
    - Default model for video generation
  • Hailuo 02
    - Alternative video generation model
  • Veo3
    - Higher quality video model
  • Veo3 [fast]
    - Faster version of the Veo3 model
  • Wan v2.2 [turbo]
    - Good for realism and dynamic movement
You can select your generation models in the
Settings menu → Advanced
section. For users on the new plans, these different models have different credit costs. The model picker displays the price of each model with a tooltip containing additional information.
These settings are available exclusively for our new plans. Users on legacy plans will have to upgrade to get access to the new premium models.
Turn into video—Transform still Images into dynamic videos
Turn into Video
You can now bring your images to life right from the Scene editor (formerly known as the Canvas.)
With the brand-new Turn into video button, you can instantly transform any image in your project into a vibrant, dynamic video clip—no extra tools needed. In just a few clicks, your still images become animated visuals, unlocking fresh creative possibilities and adding motion to your storytelling.
How it works
  1. Select any image layer in your Scene editor
  2. Click the Underlord icon
  3. Click "Turn into video" button
  4. Add a text prompt to guide the video generation and make alterations
  5. Click "Generate" to transform your image into video
You can also do this via an Underlord prompt, or directly from the
AI tools panel → Generate a video
.
With Descript's video generation, your b-roll can do whatever the moment calls for—clarify a concept, carry a metaphor, or add a spark of personality.
Transcription glossary now available for all plans
Transcription glossary is back
We're pleased to announce that we’ve returned the Transcription glossary as a feature for all plans. Previously, we limited this to Business and Enterprise Drive users as part of Brand Studio, but after receiving feedback that users valued this feature across all plan types, we've decided to make it universally available again.
If you’d like to automatically add words you correct frequently, there’s a toggle available on the Transcription glossary panel. The Transcription glossary still offers enhanced team-level features for Business and Enterprise plans, while now providing essential functionality for all users.
Quick design word limit Increased to 1200 Words
Quick Design 1200
We've quadrupled the word limit for Quick design from 300 to 1200 words. This expanded capability allows you to transform longer scripts into visually engaging content without needing to split them into smaller sections.
The new 1200-word limit is available to all users now. Simply select Quick Design from the sidebar and enjoy the expanded capability for your longer scripts.
Video regenerate (beta) improvements
We've made some upgrades to our Video regenerate feature with a new high-quality model that delivers more natural and accurate results.
What's improved
  • Better face detection
    : More accurate identification and tracking of faces throughout your video
  • Enhanced Visual Quality
    : Sharper, more detailed video output
We’re continuing to work on and improve the model. Give it a try and let us know if it performs better for you!
A reminder that this feature is still in beta, so some issues are still expected.
Rooms updates—Lossless WAV recording, Audio-only mode, and Camera resolution controls for Descript Rooms
Resolution picker Rooms (1)
This month, we’ve invested in improving quality of life across the board for Rooms users.
First, we’ve added new camera resolution controls to Descript Rooms for Hosts and Guests.
What's new
  • Resolution Controls
    : Select your preferred camera resolution directly from the pre-Room lobby page before joining a room and from the camera settings menu during your call.
  • Host Controls
    : Room hosts can now adjust resolution settings for guests, giving you more control over recording quality.
  • Quality Notification
    : When a host changes your resolution, you'll receive a notification to keep you informed.
These new controls allow you to optimize for your internet connection by selecting lower resolutions when bandwidth is limited or record at higher resolutions when quality is your priority. The resolution picker can be found in your camera settings both before and during your Rooms calls. Simply click on your camera controls to access these new options.
Lossless WAV recording
Lossless audio
Next up, we’ve added the ability to record your audio files as lossless WAV files to ensure the highest quality audio is transferred to your final project and exports.
Room hosts, co-hosts, and producers can now enable a new setting to generate lossless audio for all participants in a session. When enabled with video recording, you'll receive both a MOV file with lossless audio built in and a separate audio-only WAV file.
What does lossless mean?
WAV files are lossless audio captures and store all your audio data without compression. Nothing is thrown out, so playback sounds exactly like the original recording.
Audio Only mode
Audio Only
Finally, Audio Only mode lets you see video during your session while only recording high-quality audio. This feature is perfect for podcasters and audio-first creators who want the benefits of face-to-face conversation without the longer upload times and complex editing of video. You can toggle it on in the Rooms settings menu.
Note: When recording Audio Only, WAV files are generated by default.
Enhanced file recovery for all Descript recorders
We've revamped our audio and video file recovery system for greater reliability. Your recordings in Rooms, Editor recorder, or Screen recorder are now better protected against network issues, crashes, and other problems.
New upload features
  • Real-time Upload Progress
    : A streamlined UI shows upload status while recording.
  • Improved Upload Reliability
    : More resilient system handles poor network conditions intelligently.
  • Smart Retry Mechanism
    : Failed uploads automatically retry before full recovery.
Recovery Process Improvements
  • In-Project Recovery UI
    : Yellow "Uploading Recordings" section in sidebar shows recovery progress.
  • Universal Recovery Page
    : Visit web.descript.com/recovery to access all recoverable files.
  • Cross-Window Visibility
    : Recovery progress visible across multiple tabs and windows.
  • Simple File Retrieval
    : Download recovered files with a dedicated button.
The system works on the same device and browser that made the original recording. For best results, keep your recording tab open until uploads complete.
These improvements make recording with Descript more reliable and stress-free.
Bug Fixes
  • Fixed a bug causing editor recording to shut off prematurely
  • Fixed a bug causing partial length clips to be added to timeline after recording
  • Fixed a bug causing Underlord to ignore some remove commands
  • Fixed a bug causing insert media to fail to apply to full timeline
  • Added an error message for Veo3 failure state
  • Fixed a bug preventing account email update for some users
  • Fixed a bug preventing cohosts from stopping a Rooms recording
  • Fixed a bug causing users to get logged out when switching Drives
  • Fixed a bug preventing some enterprise users from logging in via SSO
  • Fixed a bug preventing some users from creating a Room
  • Fixed a bug causing Quick recording to arrive without audio
  • Fixed a bug causing an app crash when translating a composition
  • Fixed a bug causing an app crash when dragging into the Layer lane
  • Fixed a few bugs preventing some users from opening projects
  • Fixed a “Something went wrong” error when opening some projects
  • Fixed a crash caused by copy to composition
  • Fixed a bug causing Underlord to fail to apply Studio Sound
  • Fixed a bug causing failure of invites to be sent
  • Fixed a few bugs related to Avatar generation failure
  • Fixed a bug causing Layout pack change to fail
  • Fixed a bug causing image layers to fail to appear in export
New in Labs—Cursor Presence
MultipleCursors_v2
When you're collaborating on a project with teammates, we now display their cursors as they move throughout the composition. This makes it easier to follow what they're looking at or editing—helping everyone stay in sync without asking, "Where are you right now?"
How it works
  • See your teammates' cursors when they're active in the same project
  • Cursors appear with your teammate's name or avatar next to them
  • The composition selector shows who's currently working where
This is currently available for everyone, though some users will see it turned on by default:
  • 50% of users will have Cursor presence turned ON by default
  • 50% of users will have Cursor presence turned OFF by default
  • Everyone can manually control this setting in the Labs section the Settings menu
How to turn it on or off
  1. Open Settings in Descript
  2. Go to the Labs section
  3. Find Cursor presence and toggle it on or off
Note: Turning off Cursor Presence only changes what you see. You won't see other people's cursors, but teammates will still see yours if they have the feature on.
Try out Cursor Presence today and let us know what you think.
New in image generation—Nano Banana
image
We’re excited to add Nano Banana (also known as Gemini Flash Image) to our image generation model options.
What makes Nano Banana special?
Nano Banana excels at maintaining consistency in details across image generations, allowing you to change subtle details or take big swing without worrying about whether you'll lose the core of your prompts.
How to access Nano Banana
To enable Nano Banana for image generation:
  1. Go to Settings → General
  2. Select Nano Banana from the dropdown menu
  3. Use it with either Underlord or via AI Tools for image generation
image
Additionally, we will now place any generated images into your AI assets folder within the Project files menu immediately after generating.
Please note: If you delete them from this folder, they will be removed from your history.
New in AI Speakers—Eleven Labs V3
While we’re on the topic of new AI models, we’ve also added Eleven Labs V3 as an option for AI speech generation.
image
Eleven Labs V3 offers significant improvements in natural speech quality that can sound as good as recorded voiceover. It also supports inline prompts in brackets (e.g., [angry], [sigh]) to adjust tone, accent, or add nonverbal sounds
How to access Eleven Labs V3
  1. Go to User Settings → General → Advanced
  2. Find "Default AI speech generation model"
  3. Select "Eleven Labs V3 (Alpha)" from the dropdown menu
No additional steps are required - you don't need to create new custom voices or adjust any project settings.
Important to know
While Eleven Labs V3 offers significant improvements, there are a few things to consider:
  • This model is in alpha, meaning it is still being tested and improved upon
  • The model may struggle with consistent voice continuity across multiple generations
  • All custom voices and some stock voices are affected by the new model
Export menu updates
image
We’ve made a few changes to the Export dropdown, and added a new option to create smaller sized files when using a Descript web link.
What’s new?
  • GIF exports have been consolidated into the Video tab
  • We’ve increased the size of the thumbnail preview
  • There’s a new Optimize file size option for Descript web links
What is "Optimize File Size"?
The new toggle for "Optimize file size (slower)" allows you to create smaller video files when exporting your projects to a Descript web link. While enabling this option will add some extra processing time to your export, it can dramatically reduce file sizes.
Bug Fixes
  • Fixed a bug preventing layout change when using Create clips
  • Fixed a bug preventing clip creation w/ error message when using a Russian script
  • Fixed a bug resulting in Rooms files failing to upload
  • Fixed a bug resulting in Avatar generation failure w/ error message
  • Fixed a bug resulting in Recordings being delivered with mismatched audio/video length
  • Fixed a bug causing AI video maker to fail
Introducing Templates—Your shortcut to professional videos with Underlord
image
Templates are battle-tested workflows crafted by our engineering and video teams for popular video types. Instead of struggling to craft the perfect prompt, simply choose a template that matches your needs, and Underlord will guide you through creating your custom video.
You can find our templates are prominently featured on Descript's home screen for easy access. You'll also find them by opening Underlord in an empty project.
Just pick a template from the gallery that matches your project needs. Underlord will run through all of the prompts automatically.
Underlord will then follow-up with questions about your assets, goals, and style preferences to customize your video.
Available templates
Our template library includes options for a variety of use cases:
  • Edit a video
  • Create social clips
  • Edit a video podcast
  • Generate an avatar video
  • Make a social ad
  • Create an explainer video
  • Create introduction videos
  • And more!
Why Use Templates?
Templates eliminate blank-page panic and endless prompt-tweaking. They're your shortcut to:
  • Discover what's possible with Underlord and Descript
  • Start projects confidently with proven workflows
  • Create consistent, high-quality videos without being a video editing expert
  • Save time by following guided, step-by-step processes
Templates are available to all users. Try them today and transform how you create videos with Descript!
New in Editor—Control Multiple Layers at Once
Multiselect 2
Power up your scene design with multi-select – our most-requested editing feature for visual compositions in Descript. Now you can select multiple objects at once to manipulate them simultaneously, making your visual editing workflow significantly faster and more efficient.
Multi-select allows you to select and edit multiple layers at the same time in the scene editor. This streamlines your workflow when working with complex layouts by letting you:
  • Move, resize, or align multiple elements simultaneously
  • Make bulk property changes across your selection
  • Copy and paste multiple objects at once
To use multi-select hold Shift and click on individual layers to add them to your selection, or click and drag to create a selection area that captures multiple objects.
Then, you can manipulate your selection:
  • Move all selected objects by dragging them or using arrow keys
  • Resize all selected objects by dragging the handles of the bounding box
  • Edit shared properties through the properties panel or toolbar
  • Hold Shift and click on a selected object to remove it
Note: This is still being rolled out, so if you don't see it yet, check back later today.
Interface updates
This update adds some updates to the interface to be aware of:
  • Selected objects show a dashed outline, with a bounding box surrounding all selected items
  • Only displays properties that are common to all selected objects
  • When selected objects have different values for the same property, it will display as "Mixed"
  • The outer edges of your selection will snap to guides, canvas borders, and other objects
image
While multi-select greatly improves your workflow, there are some current limitations to be aware of:
  • Text layers don't scale in the same way as other layers when resized
  • You cannot select layers that don't share a scene or don't overlap in time
  • Bulk rotation of multiple objects is not supported in this initial release
  • You cannot change media or cropping for multiple layers at once
This highly-requested feature significantly improves the creation of educational videos and visual projects where you need to arrange multiple elements in a composition. No more tedious object-by-object adjustments – just select, edit, and create with newfound efficiency.
Other editor updates:
You can now review the prompts that were used on generated media like video and images by opening the file with View Media and clicking the Info button.
AI Image avatars (1)
Bug Fixes
  • Fixed a bug causing users to get logged out when switching drives.
  • Fixed a bug causing an recordings to result in a “something went wrong” error in projects.
  • Fixed a bug resulting in no video appearing from a Rooms recording.
  • Fixed a bug preventing some recordings from uploading.
Good-looking video, any way you generate it
You can now generate custom video with AI right inside Descript! Our new video generation feature lets you easily create unique, animated clips for your projects without relying on stock footage. Whatever (beguiling) bespoke video your social post, explainer video, or tutorial needs, you can have it. Just ask Underlord and it'll generate some video, tailored to your content.
  • AI-powered clip creation
    - Describe what you want, choose a style, and Underlord generates a 5-second animated clip.
  • Style library
    - Choose from over 20 visual styles including cinematic, cartoon, watercolor, and 3D animation to ensure consistent, high-quality results.
  • Image-to-video workflow
    - For best results, generate an image first to get the style and subject matter right, then transform it into video.
  • Script integration
    - Ask Underlord to generate videos based on your script content, automatically determining appropriate styles.
How it works:
  • Type a prompt describing what you want
  • Ask Underlord to turn your image into a video with a simple animation prompt. (e.g.,
    "Generate an image of a robot driving a bus in the style of a comic book."
    )
  • Your generated clip replaces the original image in the scene editor and appears in your timeline.
  • All generated media is saved to your AI Assets folder for future use.
For a limited time
all paid plan users(Hobbyist, NFP/EDU, Creator, Business, and Enterprise) can generate up to 3 minutes of video per month (that's 36 five-second clips!). Try it now and enhance your projects with custom animations.
Note: Each clip is 5 seconds long, and the feature is only available to paid plans.
Click here to try out the prompt we used to create the video above.
Introducing Image-to-Avatar Customization
You can now create and customize AI avatars based on images you upload. Once you've created an avatar, you can generate variations just by entering a text prompt. Adjust your avatar's background, clothing or art style. These custom avatars can then be used just like our stock avatars.
image
Just click Create a custom avatar in the speaker menu to get started.
What's New:
  • Image-to-avatar generation
    - Use any image as a starting point for your avatar. Upload an image and add a text prompt to generate a custom, styled version.
  • Restyle with text prompts
    - Continue editing your avatar after generation by adding text descriptions to refine its appearance.
  • Drag & drop support
    - Simply drag images directly into the avatar creation interface for a faster workflow.
  • Image Downloads
    - Download any generated avatar image before assigning it—perfect for reusing later or using outside Descript.
image
This update gives you more creative control while maintaining consistent quality with Descript's avatar system. Try it today to create unique, personalized avatars for your next video.
ThirdMission_BrazeModal_1_Underlord
Underlord is ready to collaborate—and it’s free. You’ll see it when you open Descript. Click the icon in the bottom right corner to start chatting with an AI co-editor that knows what a good video looks like and knows how to make it.
And did we mention it's free? From now until the end of August, using Underlord won’t count against your monthly AI limits (but using AI tools yourself will), so now is the time to take it for a spin. It’s still in beta, but getting more powerful every day.
What can the new Underlord do for you?
Execute complex workflows
. Just describe what you want, and let Underlord do the heavy lifting.
  • “Switch between multicam and single cam layouts throughout this podcast. But don’t use smart transitions.”
Translate your video and captions.
It can add dubbing or one of our native-sounding AI speakers.
  • “Dub this into French, Spanish, and Italian.”
  • “Add German captions to this video and also create a version where you dub it in French."
Create videos from slide decks.
Upload a PDF of your slide presentation; Underlord will turn it into a video. It can write a script for the talk track, if you want.
  • "Create an avatar video of these slides, with playful narration."
  • "Take this recording and this slide deck and turn it into a video about my company strategy, using the slides as b-roll."
Make and customize social clips.
It can identify the most clip-worthy moments and set them up for you.
  • "Create three 1-minute clips of high conflict moments."
  • “Make 12 vertical 30s clips in a new composition with music, social-ready captions, and visual transitions.”
Add advanced transitions and animations.
Apply scene transition effects like fades, crossfades, directional wipes, star wipes, and blurs. It can also add animations like Ken Burns, pans, and zooms.
  • "Make all transitions crossfades.”
  • "Apply a dramatic pan from left to right on this photo."
Want to see it in action?
Check out our Learn Descript tutorial.
You can learn more about effectively prompting Underlord in our Help Center.
Prefer the old way?
If you don't want to use Underlord to brainstorm, write scripts, edit your videos, make social clips, or anything, we won’t force you. For now, you don’t even have to look at it. You can turn it off in Labs settings.
Updates to the sidebar
image
This update also introduces a number of important changes to the layout of the sidebar:
  • The Underlord button has been moved to bottom; it opens the agent chat prompt.
  • The Project folder is now at the top.
  • Manual AI features like Studio Sound, Remove filler words, and Green screen now live under AI Tools.

new

improved

fixed

The new timeline is ON

Starting today, we’re toggling the new timeline experience ON in Labs for everyone.
If you haven’t had a chance to try it yet: We've completely redesigned the timeline to make video editing simpler and more intuitive. The new timeline gives you a clearer view of your video and makes it faster to trim, split, and add scenes directly from the timeline.
To open the new timeline, hover over the solid grey bar above the play button and use your mouse to drag it
up
.
This update comes with so many small changes and improvements we recommend that you view the video above as well our help center article to get acquainted.
  • Scene rail has been removed:
    Scenes now live inside the timeline, creating a more streamlined editing experience.
  • Script thumbnails:
    Scenes are now represented in the script with visual thumbnail images instead of slashes, making it easier see the timing of visuals at a glance.
  • Simplified timeline indicators:
    Comments, audio, and other elements are now shown with icons placed directly in the timeline where they occur, improving visibility and context.
  • New split button:
    Add scenes and split clips or layers with a single click, speeding up your editing workflow.
  • Improved timeline tools:
    Access tools from the toolbar by toggling on
    Advanced Timeline Tools
    from the View menu to reveal the dropdown with Select, Hand, Blade, Range, and Slip tools.
  • Storyboard view:
    Get a visual overview of every scene in your composition and quickly jump between them for easier navigation.
There’s also a new dropdown
View
menu in the upper lefthand side of the screen right next to the
Home
button. This menu contains a number of quick access options and settings for different areas of the Editor window:
  • Script - Show/Hide script and other view settings
  • Scene editor - Show/Hide scene editor and placement settings
  • Timeline - Show/Hide timeline and other view settings
  • Panels - Quick access for panels on the sidebar like Project, and Elements
  • Theme - Quick access to toggle Light or Dark mode
image
The new timeline turned on for all users. If you need extra time to get up to speed, you can temporarily opt out by disabling it in
Settings → General → Labs
. However, we'll be transitioning all users to the new timeline experience in the near future.
If you're on Desktop, we also release an update that requires a restart. It fixes a few bugs.
Bug fixes
  • Fixed an issue on Desktop causing windows to be the wrong size on app launch or restart.
  • Fixed an issue related to window focus when recording with the Screen recorder.
  • Fixed an issue with install and auto-update on Mac & Windows.

new

improved

fixed

Release Version 115

AI video maker updates
We’ve made a few improvements to the AI video maker, which you can find on the Home screen. Here’s what’s new:
  • You can now upload an audio file to start you AI video maker project.
  • For files that you upload yourself, we will use Edit for clarity, remove filler words, and shorten word gaps by default.
You can try it right now by clicking here.
image
Improved image generation
We’re using a new and improved image generator when you select “Generate an image” from the Underlord panel on the sidebar. You’ll see an overall improvement in the quality of images. This has not yet been ported over to the AI video maker, so keep in mind you’ll be seeing images generating from the older image generation model when using that tool—for the time being.
image
Drive invite links
We no longer support invite links to Drive, instead we’ve improved the experience for email invites. This helps keep Drive invites more organized and easier to track whether or not they have been accepted.
Avatar update
  • We've added new, more realistic Avatars to the gallery to give you more variety in your avatar videos.
Lifelike avatars
  • You can now select a Custom speaker from the main Assign speaker menu when creating an Avatar for your project.
image
New in Labs—a new Timeline experience
We’re rolling out a fully redesigned, and reconsidered Timeline view in Labs this week. Labs is our testing ground for new and exciting features that are still in development. You can toggle on this new Timeline experience by opening the Settings menu → General → and scrolling down to the Labs section.
image
The new timeline comes with many changes, which is why we’re putting it in Labs for users to get acquainted, and to allow more time for testing and polish.
Here’s what you need to know:
  • The scene rail has been removed, and replaced with a visual timeline made up of thumbnails broken up by scene.
  • Slashes to mark Scenes in the script have been replaced with thumbnails. These thumbnails also are smartly selected to better represent the visual content of that scene.
  • There’s a new Split button (keyboard shortcut ‘S’) that works on both Scenes and Clips, so you can add splits with a single click.
  • The timeline toolbar is now under Advanced Timeline Tools - you can toggle this on in the settings menu to the right of the playback controls.
image
You can read more about all the changes in our help center, including a video walkthrough from Andrew.
Bug Fixes
  • Fixed a bug causing images to be cutoff after cropping when an animation is present
  • Fixed a bug preventing Layouts from being applied when using Automatic multicam
  • Fixed an issue resulting in missing backup files when using Rooms
  • Fixed a bug causing a crash when using Copy to clipboard
  • Fixed a bug preventing correct text from removing spaces
  • Fixed a bug preventing Find and replace from effecting punctuation
  • Fixed a bug causing a “You must be a member of this drive” error when transcribing a Screen recording
  • Fixed an issue causing text corrections to disappear after aligning a Sequence file
  • Fixed a bug causing bulk Subtitle export to only deliver one file on Desktop
  • Fixed a bug causing UI issues when an ignored word is surrounded by cuts
  • Fixed a bug preventing publishing with a “corrupt text/audio alignment” error

new

improved

fixed

Release Version 114

New in Home—AI video maker
We’ve re-built and relabeled our AI video maker adding a host of new features including Avatars, automatic layouts, captions, titles, scenes and even b-roll.
Select AI video maker from the Home screen to get started. From here you can start generating your video by:
  • Uploading a file
  • Generating from a prompt
  • Pasting in a pre-written Script
If you select either
Generate from prompt
, or
Paste in a script
you’ll first select an Avatar to be your presenter, along with an AI speaker to voice it. If you select “Upload a file” - we’ll take you straight to generating b-roll, or auto-selecting stock media for your b-roll.
Once you’ve made your selections, the video will start generating, and you can either Export immediately, or dive in and edit it. If you’re using a pre-recorded video, but prefer an Avatar, you can always swap it out inside the project.
This tool is a great way to bring a quick idea to life, or just try out Descript’s editing features with no barrier to entry in terms of having an idea or pre-recorded material.
Screen recorder updates
image
Development of our new Screen recorder is moving forward. This week, we’re removing the Beta label.
Even more updates are coming to the screen recorder, so stay tuned.
Custom speaker quality improvements
Back in February, we rolled out major improvements to speaker quality to our Business and Enterprise users. We have improved the quality even more and are deploying both sets of improvements to all users in the coming weeks. You should notice a higher overall audio quality with better, more natural delivery. This also means that we will soon be fully deprecating custom speakers made with our very old models. These are labeled as "Removing soon" in the AI Speakers menu in Drive view. If you’re still using one, you’ll want to create a new custom speaker with the upgraded models by 6/30/2025. You can do this by clicking the "New speaker" button in the top right of the AI speakers menu in Drive view.
Editor updates
  • Adding a new stock speaker to projects that already have avatars in them will now ask if you want to add an avatar to the newly added speaker.
  • Blank compositions will hide the Scene editor until content is added for a cleaner blank page experience.
  • We’ve removed the Labs option to toggle off Regenerate in the toolbar.
General bug fixes
  • Fixed a bug where correcting the transcript would make avatars go out of sync.
  • Fixed a bug in the “Assign avatar” modal that let you click on "Assign avatar" without having one selected.
  • Fixed a bug resulting in "Error when changing the text" when trying to Create Clips in a composition with hidden placeholder layers.
  • Fixed a bug causing transcription glossary to not auto-correct words when transcribing.
  • Fixed a bug causing video layers to disappear in some translated compositions.
  • Fixed a bug causing “error changing text” when pasting between some compositions.
  • Fixed a crash resulting in "Singular matrix detected, cannot reliably invert” error message.
Rooms bug fixes
  • Fixed a broken link in the stalled upload modal that was supposed to go to the help center.
  • Fixed a bug causing upload dialog boxes to overlap.
  • Fixed a bug resulting in backups not being transferred to the media library.
  • Fixed a bug showing a cancel option next to completed uploads.
  • Fixed a performance issue in the people tab.
  • Made the upload percentage in people tab more accurate for non-host participants.
  • Fixed a bug preventing late joining users from selecting a backup file.
  • Fixed alignment issues on the partial upload dialog box. Full guest names can be seen by hovering the mouse over the name.
Load More