Synthesia Release Notes

Add burned-in captions to dubbed videos in one click, so your localized content stays accessible and easy to follow, even with sound off.

If you’ve ever shipped a localized video and then realized it needs captions, you know the drill: export an SRT, open another tool, and burn captions in manually.

Now, you can do it directly during dubbing:

• Turn on Burned-in captions when creating a dub (it’s off by default)
• Captions appear in the dubbed language and are timed to the dubbed audio
• Each language version keeps its own setting, even if you edit the transcript and retranslate

This helps your dubbed videos work better in more places:

• Sound-off viewing (social feeds, autoplay in LMS, internal comms)
• Accessibility, without extra steps

What to know

• Caption sharpness depends on your original upload quality. For crisp captions, upload 720p or higher
• Captions use a fixed style (the same style as our existing burned-in captions), and Styled Captions aren’t supported for dubbing yet

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

Pick 720p, 1080p, or 4K when generating B-roll, so you can iterate faster, control quality, and manage credits more predictably.

You can now select your preferred output resolution anywhere you generate B-roll, including Create with AI in the editor and the AI Playground.

How it works and why it matters

Before, B-roll generation was locked to 1080p. Now you can choose:

• 720p for faster, lower-cost iteration
• 1080p (default) to keep your current workflow the same
• 4K when you need the highest possible quality

You'll see an updated credit estimate based on your chosen resolution and audio settings before you click Generate, and that estimate is what gets charged.

Notes and limitations

• Flux 3 currently doesn’t support 4K
• When you add a 4K clip to a video, it’s downscaled. Download the clip if you need the full 4K file.

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

Create an on-brand Synthesia video without leaving ChatGPT or Claude. Describe what you need, pick a style, and generate a video in minutes.

Synthesia MCP is now in public beta! Synthesia MCP is a new way to create videos end to end from your chat. Available for creators on all paid plans.

How it works

Many scripts start in an AI chat tool. Now, you can stay where the work begins and still get an on-brand Synthesia video.

• Describe the video you want, or paste an exact script
• Pick your workspace and a style or template
• Generate the finished video in the chat, then watch it there
• Open the draft in Synthesia if you want to fine-tune it before generating

Get started

• ChatGPT: search for “Synthesia” in the marketplace and connect
• Claude: add a custom connector with https://mcp.synthesia.io/mcp

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

Create up to 20 seconds of B-roll with natively synced audio — and drop polished clips into your video in seconds.

If you’ve ever had the right script, but not the right supporting visuals, creating B-roll can slow everything down.

With Flux 3, you can now generate longer, more polished clips in one go:

• Generate up to 20 seconds of B-roll in a single prompt
• Get native audio (dialogue, sound effects, and ambient noise) generated alongside the video for better sync

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

Preview an avatar's animations for a single scene from the editor, so you can review and iterate on avatar performance without generating or re-generating the whole video.

You now have a way to generate, review, and re-generate avatar performance for a single scene directly from the editor. Available for creators on Enterprise plans.

How it works and why it matters

Previously, you had to generate the full video to check how an avatar performed in one scene.

Scene Preview allows you to:

• Preview avatar performance for an individual scene from the editor (if it’s already been generated)
• Generate just that scene, so you can review the result and iterate without waiting for a full video to generate
• Re-generate the avatar’s performance to better match your intended output

For example, if you update one scene in a longer video, you can preview that scene before generating the full video.

Scene Preview generates the avatar performance together with the voice. It doesn't currently re-generate the avatar performance while keeping existing audio.

To learn more, check out our documentation.

Share the base person for an avatar with teammates or your whole workspace so they can create new outfits for it and use it to generate media.

You can now share a Person (the base persona for a customizable avatar) with specific teammates or your entire workspace, so you can collaborate using the same Avatar. Available for creators on Enterprise plans.

How it works and why it matters

Until now, you could share an Outfit, but teammates couldn’t generate new outfits from the same Person.

With Person Sharing, you can:

• Share a Person with individual teammates or with everyone in your current workspace
• Use a shared Person to generate b-roll videos, new outfits, and images
• Access sharing from the Avatars page, avatar pickers, or the Person page

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

The Assistant now adds curated AI video b-roll featuring your Avatar—automatically matched to your scene, delivered in seconds, and free on all plans.

Today, we’re introducing AI Video Presets in Assistant — a faster way to get b-roll that looks made for you. Available on all plans.

How it works and why it matters

When you create a video with the Assistant, Synthesia can now automatically fill eligible b-roll slots with a curated AI video clip:

• Matched to your scene (so the visuals fit the setting)
• Featuring your Avatar (from your brand kit, in a matching outfit)
• Delivered in seconds, using a catalog of pre-rendered clips
• Free to use, with no extra prompting, selecting, or opting in

The result: your videos look more consistent and more “you,” without extra work in the Editor.

For more on how it works, check out our Knowledge Base.

Today, we’re introducing a new way to buy credits directly from the Synthesia platform and keep your balance topped up automatically.

How it works and why it matters

You can now manage credits right from your billing dashboard:

• Buy credits on demand when you need them
• Set a balance threshold, then enable auto top-ups to automatically replenish credits

This is especially helpful for long-running jobs (like sessions or dubbing) where running out of credits mid-process could cause failures. With auto top-ups, you can keep work moving without interruptions.

Learn more about buying credits and setting up auto top-up in our Knowledge Base.

Motion Graphics now use your brand kit fonts by default, and update automatically when you switch brand kits—so every graphic stays on-brand.

Your Motion Graphics will now automatically use the fonts from your selected brand kit. Available for creators on Enterprise plans.

What’s new

• New Motion Graphics are generated using the fonts in your selected Brand Kit (previously created Motion Graphics keep the fonts they were generated with)
• If you apply a different Brand Kit to your video, Motion Graphics update their fonts automatically—just like other text
• You can also update Motion Graphics fonts after generation, so it’s easier to stay consistent as your brand changes

Get a clear breakdown of credit usage with a new Billing API endpoint, so you can reconcile spend and troubleshoot changes with confidence.

With Synthesia’s Billing API you have a new way to pull a credit usage breakdown programmatically.

How it works and why it matters

If you’re tracking usage in your own systems, you can now fetch a breakdown of credit usage via API. This makes it easier to:

• Reconcile usage across tools and time periods
• Understand what’s driving changes in credit consumption
• Build internal reporting that matches your billing dashboard

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

Reassign, create, and rename speakers in a dubbed video with one click—available on Enterprise plans.

You can now edit the speaker attribution, create new speakers, and rename then in your dubbed videos. Available for creators on Enterprise plans.

How it works and why it matters

Dubbing relies on automatically detecting who's speaking. That detection doesn't always get it right—a line can end up attributed to the wrong person, or a distinct voice can go undetected entirely. Until now, fixing that meant either living with an unusable dub, or correcting it word-by-word and still ending up with awkward pauses in the result.

Now you can fix it directly:

• Reassign a speaker on any segment with one click, when a line's been attributed to the wrong person
• Create a new speaker if someone's voice wasn't picked up as distinct—this builds a unique voice clone from the audio you assign to them
• Rename speakers with real names instead of "Speaker 1, 2, 3," so your team can review edits without guessing who's who

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

Design any scene with Layouts: a library of 100+ ready-made designs right in the Editor, with instant theme previews and one-click swaps in Storyboard

There's a new way to design a scene in Synthesia: Layouts. Add a new scene to your video and you'll find a Layouts tab right next to Template—a library of 100+ ready-made scene designs you can browse and apply with a click. Live today for all Synthesia creators.

How it works

Add a new scene to open up the Layouts menu (next to Template).

From there you can:

• Start with Suggestions: our picks for what fits the content already in your scene
• Or browse by type: Intro, Speaker, Media, Text, Numbers, and more
• Preview different themes before committing: see the same layout in a few different looks. If you're not on Enterprise, this is where you'll find our four built-in styles (Ember, Bloom, Dusk, and Crimson) so your scenes look polished from the start
• Apply with one click: your script and content stay exactly as they are, only the design changes

This isn't limited to scenes you build by hand: Assistant draws from the same layout library, so videos it puts together for you get the benefits too.

What you can do

• Browse and apply Layouts that match what you're trying to say
• Preview a Layout with different themes before you commit
• Swap Layouts in Storyboard to try a new design quickly, without retyping anything
• Undo a Layout change if the previous version worked better