We’ve made some major improvements to working with Text elements like captions and overlays.

Here are the details:

And finally, adding periods to abbreviations and numbers will no longer add a line break to captions. This would normally be in the bug fixes section, but it was such a long standing issue that we thought you’d like to know that it is finally fixed.

Descript now automatically detects and transcribes the correct language of your audio, making it easier to work with content in different languages. When uploading new files, "Auto" is now the default language option in the transcription settings.

Existing users who have already set their preferred transcription language won't be affected by this change. You can still manually select a specific language from the dropdown menu in the transcription settings, or set a specific default language in the general Settings menu.

You can now add a blur effect to the background of speaker focused videos. This can be toggled on from the Layer menu for any video track, and will blur out everything behind the speaker. There is an intensity slider for more or less blur. Please note, this only works with human speakers. Pets, inanimate objects, and ghostly apparitions will be blurred as if they are part of the background.

Generating text-to-speech is now supported in 19 languages, and we will auto detect the language of the text that is entered. You can enter TTS in: English, Spanish, French, German, Italian, Portuguese, Polish, Czech, Dutch, Romanian, Turkish, Danish, Malay, Finnish, Hungarian, Norwegian, Slovak, Croatian, Swedish.

Our translation powers when using stock speakers has expanded from 5 supported languages, to 21 supported languages. The full list of languages that support dubbing: English, Spanish, French, German, Italian, Portuguese, Hindi, Polish, Czech, Dutch, Romanian, Turkish, Greek, Danish, Malay, Finnish, Hungarian, Norwegian, Slovak, Croatian, Swedish.

For Business and Enterprise users, the following languages will also have the benefit of our new Recommended voices which are designed specifically for them: Spanish, French, German, Italian, Portuguese (BR), Polish, Dutch, Hindi, Turkish, and Swedish.

This brings the total number of languages with Recommended voices to 10.

With our first update back from the holidays, we’re adding a new way to export your translated compositions in bulk, retiring jibber jabber, making some small tweaks in the editor, and fixing a number of bugs.

You can now export all of your translated compositions in a batch process. We’ve added checkboxes to the Language selection list on the Export tab, so just select all the translated versions you’d like exported, and they’ll be automatically queued up and processed. A great time saver on the path to expanding your audience.

We’ve made it easier to understand when you’re nearing your text-to-speech limit by eliminating Jibber Jabber (replacing random words with nonsense when you’ve used your balance.) Now, we’ll simply stop generating new TTS, and you can increase your monthly limits by upgrading if you need more time. You’ll hit this prompt and click or dismiss it.

You’ll only hit this once, and then be met with a smaller prompt as a reminder that you are out of text-to-speech minutes.

We’ve added a new layer type in the Elements panel called Placeholder layers. These layers are designed to be used with the Replace media function we added a few weeks back, and are the perfect way to rough in your projects, templates, or layouts until you’re ready to swap in your final video or file.

Like any other layer type, Placeholder layers have customizable properties, including access to opacity, borders, and animations from the Layers panel. It also includes one special property exclusive to the Placeholder layer type: , where you can leave yourself a reminder about what this layer is going to be.

When you’re ready to swap in your final content, just select the Placeholder layer and click Add media or select Replace media from the right-click menu.

Translation in multiple languages can now be done all at once with this handy dropdown.

Your translations will then be available from within the composition view using the dropdown menu in the upper left corner of the Composition. When using this for captions-only, the completion time is extremely fast.

If you go back for more translations, we’ll mark any languages you’ve already generated with a green dot.

If you submit a new translation for one of existing languages, it will overwrite it with a new version. This will also overwrite any corrections you’ve made. We’ll show this warning just in case.

We hope to add the option to export translations in batches in the future as well.

There are new high quality stock speakers available exclusively for dubbing in our 4 supported languages: French, Italian, German, and Spanish

These new stock voices, provided by 11Labs are designed for the target language, and will provide much better results than our standard sock voices when working with a non-English language translation. These voices will be rolling out slowly, but you should have access by the end of this week.

Note: These new voices are available on Business and Enterprise plans only.

We’ve added a new feature to Labs called Smart transitions. This is a new style of transition that can be added between scenes. This is a powerful tool for transitioning between different layouts, as smart transition will smoothly rearrange, zoom, and fade elements on the fly.

Add fades ON: Fades are added between non-contiguous layers (i.e. two separate clips.) Fades will NOT be added in contiguous clips that cross the scene barrier.

Add fades OFF: We will not fade any layers.

We’re excited to get some early feedback on this feature so please give it a try and let us know what you think using the Feedback button in the Settings → Labs menu.

Descript’s new Desktop experience is also available from the Labs menu. This new desktop app put the speed and performance improvements of our web version into a local package. If you’ve been using the Desktop preview, this is the soon-to-be-final version.

Be among the first to switch over and enjoy the benefits.

We’re making a change to the terminology and interface around replacing your script with AI Speech. The term Overdub is going away, and it will now be considered a part of the Regenerate feature. When you highlight a section of your Script, you’ll see an option on the Script toolbar labeled Regenerate.

This will launch a modal with the highlighted text present. If you do not edit the text, it will regenerate the section with an AI voice that sounds like the speaker. This is great for changing the tone or delivery without altering the exact words that were used.

When you edit the text, you’ll be required to provide voice authorization for that speaker. This works exactly as Overdub works today, just with a different label and streamlined interface. You’ll also notice that the option to Replace with a recording has been moved into the Record panel. Just highlight the text you want replaced with a recording an open the record panel to access this feature.

If you’re wondering why we did this: we’ve found that many users find the term Overdub confusing, since it already has a specific meaning in production circles. Renaming it to Regenerate makes it clearer what it will do.

We have migrated the Descript status page to a new service provider. Here’s what you need to know: