Synthesia Release Notes

Translate videos without text overflow

Translations adapt to each text box, and long strings scale down to keep your slides looking polished.

Translating a video into a new language has always come with a catch: the translated text often doesn’t fit the layout it lands in. That means manually fixing text elements scene by scene, for every single language.

We’ve optimized our translation workflow to better fit the space each text element has on your scene, so your scenes are more likely to stay true to your original layout.

How it works and why it matters

When you translate a video, on-screen text can expand in some languages and overflow its layout. That’s one of the biggest sources of manual work in a translated video—and it’s exactly what we’ve been working to fix.

What’s new:

• Translations take each text box’s available space into account, so the translation engine generates text sized to fit the existing box (not just a literal, line-by-line translation)
• If a translation still runs long, SyRen (our AI rendering model for creating video scenes) proportionally scales the text down so it fits without breaking your layout

Why you’ll care:

• Your translated videos are more likely to look ready to share without slide-by-slide fixes
• Less manual touch-up per language makes it faster (and cheaper) to add more locales

For more on translating videos, check out our documentation.

Upload and dub up to 10 videos in one go—set languages and options once, then let every file process in the background.

You can now dub multiple videos in one go. Upload up to 10 files, choose your settings once, and we’ll dub each video in the background.

What’s new

If you’re localizing a library of content, the old flow meant repeating the same steps video after video. Bulk Dubbing Upload turns that into one batch—so you can stay consistent and save time.

Upload a batch

• Drag and drop up to 10 videos on the Dubbing page, or select them from your computer
• See a thumbnail, upload progress, and status for each file
• Rename or remove videos before you submit

Set your dubbing settings once

• Choose your target languages
• Pick full dub with lip-sync or audio-only dub
• Set lip-sync and video timing options for the whole batch

We handle the rest per video

• Source language detection runs automatically for each file
• If detection fails for a file, you can set the source language for that video
• You’ll see one credit estimate for the full batch before you submit

For more on how it works, check out our documentation.

Set custom duration, aspect ratio, and visual references when generating B-roll videos and images.

You now have more control in Create with AI, with new generation settings that help you steer B-roll videos and images so they better match your desired output.

What’s new

Instead of generating a single fixed type of output, you can now fine-tune how your generated media looks and feels:

• Choose a custom video duration for generated B-roll video (for example, four, six, or eight seconds)
• Pick an aspect ratio for generated images, including 1:1, 3:4, and 4:3
• Use visual references (an Avatar or Space) so generated images stay more consistent with the style of your scene
• Convert an image to a video directly from the asset menu

This gives you more control over framing, consistency, and pacing, with fewer iterations.

More faithful PowerPoint imports with better text parity, table support, and automatic scripts when speaker notes are missing.

We're improved our PowerPoint import tool so it functions as a more intuitive way to bring your existing PowerPoint presentations into Synthesia.

What’s new

When you import a deck, your scenes now come through with fewer manual fixes needed:

• More consistent text formatting and positioning
  • Better alignment, sizing, and spacing to match your original deck
  • Line height is handled per line (so small text no longer ends up with oversized spacing)
  • Support for paragraph spacing (space before and space after)
  • Cleaner bullet and numbered list styling
• Table support: tables are imported as motion graphics, and text is edited via the motion graphics text editor
• Automatic script creation: if a slide has no speaker notes, we’ll generate a starter script based on the slide text
• Automatic resizing for 4:3 decks: 4:3 presentations are automatically converted to 16:9 on import

Add borders to images, videos, and GIFs—inside, outside, or centered—without extra shape layers.

You can now add borders to images, videos, and GIFs.

What’s new and why it matters

Before, adding a border meant building a workaround: placing a shape behind your media, lining it up perfectly, and then managing multiple layers any time you resized or animated those elements.

Now, borders are built-in:

• Add a border directly to an image, video, or GIF
• Choose how it sits: inside, outside, or centered
• Combine borders with rounded corners

A few ways you might use it:

• Frame screenshots and screen recordings in product walkthroughs
• Add clean padding around media elements
• Create layouts and custom templates that are better aligned with your brand

Create glows, sunsets, and multi-tone brand gradients with up to five editable color stops.

Create and use gradients with up to five color stops for text and shape fills and scene backgrounds.

What’s new

Before, gradients were limited to two stops, which made it harder to create effects like glows, sunsets, or multi-tone brand gradients without workarounds.

Now, you can:

• Add up to five stops by clicking the gradient bar
• Remove a stop by double-clicking it or dragging it off the bar
• Set a unique color and opacity for every stop
• Drag stops past each other to reorder them

We’ve also added new presets to help you discover what’s possible (including a transparent outer glow).

Meet new EU and California transparency rules with automatic C2PA metadata, Content Credentials, and on-video labels—so you can publish with confidence.

We’ve added Content Credentials and labels to Synthesia: automatic metadata and on-video labels that help you meet new transparency requirements like EU AI Act Article 50 and California SB 942. Available on all plans.

How it works and why it matters

Before, meeting AI transparency requirements could mean manual reviews, policy checks, and uncertainty about whether each video included the right disclosures.

Now, we automatically add the information viewers and regulators expect:

• C2PA metadata is added to videos generated (or modified) in Synthesia
• Content Credentials appear in the video player

You can also add a visible label when you need it:

• Choose a pre-built label from the Media panel
• Customize the text style, font, and color like any other shape
• Place it anywhere on your video

This helps you stay compliant with less effort, and gives your viewers clear context about how the video was made.

For more on how it works, check out our knowledge base.

If the source video changes after you export an XLIFF, we now reconcile safe updates automatically—and flag major changes so you can re-export.

We’ve made XLIFF imports smarter, so your translated video stays aligned even if the source video changed after you exported the XLIFF.

This update helps when translations take days (or weeks) and the source video gets small tweaks in the meantime.

How it works and why it matters

When you import a translated XLIFF, we now check whether the source video has changed since that XLIFF was exported:

• If changes are cosmetic (like an updated Avatar look or backdrop), we’ll automatically import against the latest version so you don’t need to re-export
• If changes are structural (like a scene or on-screen element being added or removed), we’ll stop the import and show a clear message so you can re-export from the updated video

For more on how it works, check out our documentation.

Motion graphics now translate as part of the standard video translation flow.

You can now translate Motion Graphics generated with Synthesia along with the rest of your video. Available for creators on Enterprise plans.

What’s new

When you translate a video that includes motion graphics, the motion graphic content now translates as part of the standard flow.

• No need to regenerate motion graphics per language
• Motion graphics stay in sync with translated narration and captions
• Works across all available languages, including non-Latin scripts

This removes a manual step from localization and helps keep multilingual videos consistent and polished.

For more on how it works, check out our knowledge base.

Pick a preset, add an avatar and a space, and generate B-roll without prompting.

We’ve just shipped AI video presets—a library of pre-built B-roll presets that help you generate cinematic clips without the prompt lottery. Available on all plans.

How it works and why it matters

Instead of starting from a blank prompt, you can now pick a preset and generate reliable B-roll in a few clicks:

• Choose a preset (for example: talking, walking, working)
• Pick your model
• Add any stock or personal Avatar, plus a Space
• Optionally add your branding (for Avatar plus Space presets)

You’ll get a ready-to-go clip you can drop straight into your video—saving time on experimentation while making your content more engaging.

For more on how it works, check out our documentation.

Today, we’re introducing Avatar Customization 2.0: a more visual way to create Avatar outfits and Spaces, with better realism and more control over how your Avatar fits into your scene. Available on all plans.

How it works and why it matters

Avatar Customization now puts inspiration and composition first, so it’s faster to find a look you like and make it work in your layout.

• Improved visuals (lighting, contrast, and color) for more realistic results
• Coordinated styling that can automatically apply your Brand Kit to outfits and Spaces (Enterprise only)
• New pose and composition options, including seated Avatars and left/right positioning
• Edit outfits and Spaces with prompts to fine-tune the result
• Creators in Enterprise workspaces can also upload a reference image for an outfit or Space, so your Avatar can match a real environment (like your office or store) or a specific uniform
  • This helps your videos feel more true-to-life and relatable
  • It also saves time: instead of writing prompts, you can upload what you need and get a ready-to-use Avatar in minutes

For more on how it works, check out our knowledge base.

We've upgraded our Voices page. It's now a faster way to browse Synthesia’s stock voice library, preview voices with your own script, and download audio clips. Available on Basic plans and up.

What's new

The Voices page now includes a browsable library of stock voices organized by language.

• Filter by accent and other voice attributes
• Select a voice to listen to a preview
• Type a short script to preview how it sounds, then download the audio clip

This makes it easier to find the right voice for your content, and to generate voiceovers you can use outside of Synthesia.

For more on how it works, check out our documentation.

Stay current with voice variants

Voices are now selected based on their latest improvements, with the option to choose specific variants or revert to an older sound.

Members on free and restricted licenses can now edit scripts and add screen recordings (with permission), without needing a full license.

We’ve expanded editing access for free and restricted licenses, so more people on your team can help polish videos without needing a full license on Enterprise plans.

What’s new

Members (not guests) on a free or restricted license can now contribute when they’re invited to a video with edit or full access.

They can:

• Edit the script in existing scenes
• Add a new screen recording as a new scene
• Preview their changes

This makes it easier to collaborate with reviewers, translators, and subject-matter experts—without copying scripts into other tools or sharing logins.

Please note that free and restricted members still can’t create new videos, and their editing actions stay focused on collaboration (not full creation). Inviting members on free or restricted licenses to videos with full access allows them to invite other collaborators.

For more on how it works, check out our knowledge base.

Voices are now selected based on their latest improvements, with the option to choose specific variants or revert to an older sound.

We’ve added Voice variants to Synthesia—giving you the latest voice improvements by default, with more control when you need consistency. Available to creators on Basic plans and up.

Some voices now have multiple variants, which can sound slightly different or support different capabilities.

• By default, voices use Auto, so you automatically get the latest improvements
• If you prefer a specific sound, you can choose a variant from Voice settings

As part of this update, we’ve also remastered a set of stock voices to unlock improvements like pronunciation controls. If you’re sensitive to changes in a voice you’ve been using, you can switch to an older variant.