We’ve made the decision to turn off the YouTube import feature in Descript for now. We want to share a bit of context about why.

Over the past several months, YouTube imports have become increasingly unreliable. Success rates dropped significantly, and many videos simply stopped importing altogether.

YouTube regularly updates its systems to prevent automated downloading. These changes directly affect tools like ours, and they can break or limit importing with little notice. We’ve evaluated short-term and long-term options, but at this point we are not able to provide a version of YouTube import that works consistently over the longterm.

We hope to revisit this in the future, especially if conditions change, but we don’t want to offer a feature that fails unpredictably or creates confusion.

You can still work with YouTube content in Descript you’ll just need to download the videos manually first, then import the files directly into your project. We know this adds an extra step, and we’re sorry for the inconvenience.

If you’re downloading your , the most reliable option is YouTube Studio, where you can download the original files you uploaded.

Here’s how:

Go to YouTube Studio and sign in with the account that owns the video.

Click in the left sidebar to view your uploads.

Hover over the video, click the menu (three dots), and select .

Drag the downloaded file into Descript or add it from the Project panel.

Using YouTube Studio is the most stable, YouTube-compliant way to access your own videos and avoids the issues that affected our previous import feature.

When you translate and dub a video you can now apply lip sync to match the speaker's mouth movements to the translated audio. This makes translated videos look more natural and seamless.

To use lip sync:

Lip sync is only available on our updated plans using AI credits.

Lip sync only applies to faces detected in your video's main camera layers—it won't affect screen recordings or b-roll footage.

When you start a new video with Underlord, you can now a multi-step, multi-question Project brief that outlines the plan before any editing begins. Underlord will propose a direction for your video—including stylistic choices—and wait for your approval before taking action. This helps you feel confident about the approach before credits are spent. You can iterate on the style and direction until you're ready to move forward.

To use it, start with a template, type a prompt, or upload files to an empty composition. Underlord will present a plan and style options you can adjust before it begins editing.

You can now select Kling O1 as your video generation model in Descript. This model generates high-resolution, cinematic visuals and can create videos up to 10 seconds long.

To use Kling O1, open the model picker in your video generation settings or in the Generate video panel.

We’ve also added Flux 2 Pro as an image generation model in Descript. This model balances speed and quality, with improved text rendering and capabilities for restyling existing images.

To switch models, go to Settings → General and select Flux 2 Pro from the image generation model dropdown, or select it in the Generate an image panel using the model picker.

The Learn Descript team has been hard at work making new content to help you navigate our latest features. Today’s video covers advanced video generation. You’ll learn about:

If you’re looking for a more basic tutorial on video generation, check out this video first.

You can now select Gemini 3 as your AI model in Underlord. Google's latest model has been impressive in testing for complex tasks and multi-step workflows. The areas it does well:

To switch models, open the model picker in your Underlord settings.

You can now select Nano Banana Pro as your image generation model in Descript. This is Google's state-of-the-art model for high-resolution image generation and precise editing.

Nano Banana Pro offers many improvements of over the original Nano Banana model:

To use Nano Banana Pro, go to Settings → General and select it from the image generation model dropdown or select it in the Generate an image panel using the cube icon.

You can now extend video clips using Underlord when you need more footage. The new Extend Video option generates additional frames from the last moment of your clip, making it useful when a clip is too short or you need more content without reshooting. Or when you just need to get weird with it.

To extend a video:

The extension uses the last keyframe of your clip as the starting point. If you have scenes in your project, the extension will automatically fill the remaining time in the current scene up to your model's maximum duration.

For best results, choose clips with smooth, steady motion like a person walking or a camera panning. Avoid clips with abrupt cuts or mid-action endings.

You can extend generated clips, recorded media, or imported content.

When you translate a video with dubbing, you'll now see a progress indicator in the sidebar that shows which translations are currently processing. You’ll also see indicators above each section as it’s being translated in real time.

The updated loading state makes it easier to track multiple translations at once and gives you a better sense of how long the process will take.

We’ve introduced some improvements to our language dubbing engine. When you translate and dub a video, the translated audio should match the timing of the original audio more closely. The updated translation system better preserves the pacing and rhythm of your original speech when generating translations, so the dubbed version sounds more like your natural delivery in the target language. This improvement applies automatically when you translate and dub your videos—no additional steps required.

You can now create and save custom templates in Descript. When you find a prompt that works well with Underlord, save it as a template so you can reuse it anytime—no more copying and pasting prompts.

To create a template:

Your saved templates will appear in the template gallery under "Created by me."

Custom templates are private and visible only to you. You can't edit or delete them after creation, but these features are planned for future updates.

Click here to try it now.

Descript now supports 39 additional languages for translating captions and dubbing.

Bulgarian, Filipino, Indonesian, Russian, Tamil, and Ukrainian

English (UK), Spanish (Spain), French (Canada), Portuguese (Portugal), and Chinese (Traditional)

Regional variants apply to captions only—the dubbed voiceover will use the standard language without a regional accent.

Afrikaans, Armenian, Assamese, Azerbaijani, Belarusian, Bengali, Bosnian, Welsh, Estonian, Galician, Hausa, Javanese, Georgian, Kazakh, Luxembourgish, Macedonian, Malayalam, Marathi, Nepali, Punjabi, Sindhi, Somali, Serbian, Swahili, Telugu, Thai, and Vietnamese

You'll find these new options in the Translate menu under AI Tools.

Check out the tutorial on Learn Descript for more.

Add a frosted-glass effect to any shape or text element in your project. Glass blur softens the appearance of content underneath the element, making it useful for directing attention or obscuring things you don't want to show in your videos.

To use Glass blur:

Glass blur is a visual effect only and should not be relied on to securely hide sensitive information. For secure redaction, use a solid shape with 100% opacity instead.

When you upgrade to a different subscription plan mid-cycle, you'll now see the prorated cost displayed during checkout. Previously, the full price was shown even though you were only charged the prorated amount.

This fix ensures the checkout flow accurately reflects what you'll pay when upgrading between plans.

The bug fixes section will now include the effected app surface for easier reference. The bugs in this list largely come from direct user reports.

Drive admins on Enterprise plans can now restrict what assets are used by their team by setting permissions in Brand Studio. This helps you enforce brand compliance across all projects without constant manual review.

When you set permissions, team members will only see approved brand assets in their editor. Your brand colors, fonts, logos, and media appear first in color pickers, font menus, and media browsers—making it easy for your team to stay on-brand by default.

To set up permissions, open Brand Studio from your Drive, go to the Permissions tab, and choose brand assets. This feature is available on Enterprise plans.

For editors on Enterprise drives, you’ll now see a tab for brand-approved assets in your Media panel.

We’ve also added Sora 2 to our generative video options in Descript. Sora 2 creates cohesive multi-shot videos from text prompts, with smooth motion, camera continuity, and cinematic realism.

Sora 2 automatically generates audio including music, sound effects, and speech when you include quoted dialogue in your prompt.

Learn more about the best ways to generate and use video in Descript with our friends at Learn Descript.

We've upgraded to Veo 3.1 and Veo 3.1 [fast], Google's latest video generation models. These replace the previous Veo 3 and Veo 3 [fast] models.

Veo 3.1 maintains the same pricing and capabilities as Veo 3, while delivering improved video quality. All existing generation features work the same way—just with better output quality from the upgraded model.

You can now customize settings based on the AI model you've selected for image and video generation. Different models support different parameters, and the interface will show you which settings are available for your chosen model.

For video generation, depending on the model, you can adjust:

For image generation, you can configure model-specific parameters like number of outputs and other settings that vary by model.

These settings appear in the generation panel when you're using the AI Tools sidebar or working with Underlord. The available options update automatically based on which model you select, so you'll only see parameters that your chosen model supports.

You can now use Underlord directly from the media library in the Project panel. When you open an image or video in the preview popout, you'll see an Underlord button with options to generate new content based on that file.

This gives you the same generation options that are available from the scene toolbar, but now you can access them right from your media library.

We’ve made it easier to setup your Rooms session, before you ever start recording. You can now create invite links that automatically assign participants a specific role when they join your Room. This means you can send different links to different people based on what they need to do in the session and pairs well with Control Room—available exclusively to users on Business and Enterprise plans.

When you click the Invite button, select a role from the dropdown:

Each role has its own unique invite link that doesn't expire. When someone joins from a role-specific link, they'll automatically have that role assigned.

This is useful if you have a fixed cast or want to share a link with viewers who shouldn't be recorded. You can still manually change someone's role when approving their join request if needed.

We’ve added the ability to generate a still image from any frame in your Project. This is helpful when you want to use a specific frame from your composition as a reference image for video generation, but you can also use it for basic stills / thumbnails from your project, fulfilling a long-standing feature request.

To save a keyframe, position your playhead where you want to capture the frame, then click the Layers button in the the Scene toolbar → camera icon to save the current frame to Project files. The captured image will be saved to a "Saved keyframes" folder in the Project panel.

This works well for creating animated title cards—you can design your text and graphics in Descript, capture the frame, and then use it as an input for generating video animations.

You can now transcribe audio and video in Welsh. To use it, manually select Welsh from the language dropdown when transcribing your file.

Since this is still in beta, Welsh transcription will not be detected automatically if you use the "Auto detect language" option. You'll need to select Welsh manually each time you transcribe.

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 .

The demo will cover how to use generate video features in your editing workflow, including:

The session will include a Q&A segment where you can ask questions about the features.

Register at: https://luma.com/descript-season-11

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.

You can find the new top ups by opening the Settings menu → Plan section, and clicking

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.

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.

We’re updating the way that copy and paste works in relation to Scenes and Scene boundaries.

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.

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.

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.

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:

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.

You can now select which AI model powers your Underlord editing assistant through our new model picker, which includes Claude Sonnet 4.5.

Different editing tasks benefit from different AI approaches, so we've integrated several powerful models including the latest from Anthropic. Whether you need lightning-fast responses or deep creative understanding, you can now choose the right AI for each project.

Each AI model offers unique strengths for different editing scenarios:

Our testing with Claude Sonnet 4.5 demonstrates notable improvements in script editing quality, content writing capabilities, and performance with complex multi-step prompt templates, while being a somewhat less reliable in interacting with our built in tools like captions, and translation.

We’re still testing and refining how these models perform in the Editor, and we’d love for you to join us in pushing the limits.

You can switch models anytime by clicking the model icon at the bottom of the Underlord chat panel. While premium models deliver enhanced results, they do use more AI credits, so you can always select the option that best fits your current needs.

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.

Your Descript Free plan now includes:

We've also expanded your access to AI-powered editing in Descript, including:

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.

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.

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 , and image models like . They can also provide better character consistency across image generations, maintaining appearance and identity across different angles and scenes.

The following image generation models are available:

The following video generation models are available:

You can select your generation models in the 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.

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.

You can also do this via an Underlord prompt, or directly from the .

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.

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.

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.

We've made some upgrades to our Video regenerate feature with a new high-quality model that delivers more natural and accurate results.

We’re continuing to work on and improve the model. Give it a try and let us know if it performs better for you!

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.

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.

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.

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.

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.

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.

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.