Synthesia Release Notes

Create branded, animated infographics — timelines, flows, charts, and more — right inside Synthesia. No separate design tool, no design tickets.

Today, we're giving Motion Graphics a proper introduction — and introducing the model behind it. Motion Graphics is the first capability powered by SyRen, Synthesia's own AI rendering model for generating video scenes. It's built so anyone can create engaging video, with no design expertise required. And over time it will power much more of what you see on screen.

Now you can create professional animated scenes directly in the Synthesia Editor or with Assistant — generated from your script, in your brand, in just a few clicks. Explaining a process? Comparing options? Highlighting growth that matters? Pick from a library of templates or prompt something fully custom to bring your content to life. Already one of the fastest adopted capabilities we've ever shipped, and available now on all plans.

Why we built it

Showing complex information in video like steps, decisions, timelines, and processes has always required custom design work. That means design tickets, weeks of back-and-forth, or stock visuals that don't match what you're actually saying. Most teams just give up and fall back to bullet points, and the result is videos that look like narrated slide decks.

We believe creating visually engaging video shouldn't require design expertise. So we built motion graphics directly into Synthesia — animated, on-brand, with sound effects included.

What's new

• Your Brand Kit, applied automatically. Fonts and colors from your Brand Kit are applied to every motion graphic, so the output is on-brand and ready to publish. Not on an Enterprise plan? Choose from a selection of built-in styles instead.
• A growing library of templates. Timelines, checklists, process flows, charts, stat callouts, and more, covering the most common business communication formats. Generate motion graphics in any scene from the new entry point in the Editor.
• Edit the text, no regenerating. Once a motion graphic is generated, fine-tune the copy inside it directly in the Editor side panel, so you can get the wording exactly right without starting over.
• Polished by default. Run a motion graphic full screen or alongside your avatar at half size, with matching sound effects included automatically. And when you create a video with Assistant, motion graphics are generated for you wherever your content fits: numbers become a chart, options become cards, a process becomes a flow.
• Prompt for fully custom motion. Describe what you want, or upload a rough sketch or existing diagram and turn it into motion. It's your go-to when templates won't cut it.

What's next

This is the first of much more to come from SyRen. Over the next year, SyRen is going to change the way you create video in Synthesia. It's the engine that will power layouts, scenes, and almost everything you see on screen, and we'll keep investing in it so you can create rich, engaging video without needing to be an expert designer.

We can't wait to see what you create. To learn more about how to use motion graphics, check out our documentation.

Add preset sound effects to entrance and exit animations.

Today, we’re introducing animation sound effects — a faster way to add polished audio moments when you animate elements. Available on Basic plans and up.

How it works and why it matters

• Add an Entrance or Exit animation to any element
• Click the sound icon in the animation popover
• Pick a preset, adjust volume, and preview

The sound effects are tied directly to the animation, and that means fewer workarounds, faster iteration, and more confident publishing.

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

Generate and edit video from text, image, and audio with Gemini Omni Flash, Google's newest model — now available in public preview inside Synthesia.

Just hours after Google opened public preview, and now Gemini Omni Flash is live inside Synthesia. Generate a scene with this state-of-the-art model using a prompt.

We want to give you access to the best models out there, not just our own, so you can unlock more engaging, creative video without ever leaving Synthesia.

Live now on self serve plans, and coming soon for Enterprise (if you’re on an Enterprise plan and want it now, reach out to your Customer Success Manager). To learn more about how Google Omni Flash works in Synthesia, check out our documentation.

A set of small (but satisfying) Editor improvements to resizing, trimming, stock search, and restyling actions.

We’ve rolled out a set of small, high-impact improvements that make everyday editing smoother and more predictable.
These updates focus on the moments where you’re moving fast: adjusting shapes, trimming clips, searching for B-roll, and fine-tuning captions. The result is less friction, fewer mis-clicks, and a cleaner editing flow.

More precise design controls

X and Y positions update live while cropping, so layout changes feel more accurate

Set per-corner radius on multiple elements at once (as long as they're rectangular to begin with)

The gradient angle dial no longer blocks resize handles for shape and text elements

Faster and cleaner media editing

Video trimming now includes a Reset button to restore the full clip in one click

Stock video search now has a duration filter, so it’s easier to match your scene length

UX/UI fixes that keep you in the flow

• Repeated clicks on the same context-menu action are now blocked to prevent accidental double actions
• Entering trim mode for a video element with the Inspector panel expanded no longer causes the whole page to scroll sideways
• The rounded border on the active word in dynamic captions now renders in the preview, matching the final output
• Dynamic captions no longer blink while being dragged
• Undo after deleting an element now re-selects it (we all make mistakes)

Today, we're releasing our rebuilt pronunciation controls — a ground-up rethink of how pronunciation works in Synthesia. You can now speak a word once to set its pronunciation, preview how it sounds before saving, apply it across your entire video in one click, and save it to a Glossary that works across every voice in your workspace automatically. Available now on all plans.

Why we rebuilt it

Pronunciation has been one of the most persistent sources of frustration in Synthesia. The old system asked you to type phonetic spellings and guess at the output — and even when you got it right in one scene, it wasn't guaranteed to sound the same in the next. The Glossary only worked for one voice at a time, meaning teams had to repeat the process every time they switched avatars.

For teams whose videos depend on getting a company name, product, or acronym right — this wasn't good enough. So we rebuilt it to allow you to set a pronunciation once, trust it every time, and eliminate time wasted trying to get a single word right.

What's new

• Speak to set a pronunciation. The fastest way to get a pronunciation right is to say it yourself. Open the pronunciation menu on any word, hit record, say the word, and the system handles the rest — no phonetic spellings, no guessing. Preview the result before you commit, and re-record if you want to try again.
• Type a pronunciation with consistent output. The typing input is still there, now producing more consistent results across supported voices than before.
• Preview before you save. Every pronunciation — whether you spoke it or typed it — goes through a preview step before it's saved. Hear exactly how the word will sound before it's applied anywhere. No more generating a full video to discover a word still sounds wrong.
• Bulk apply in one click. Once you're happy with a pronunciation, apply it to every instance of that word across your entire video at once.
• A Glossary that works across your whole workspace. Pronunciations saved to the Glossary now apply automatically across all voices in a language — not just the voice you set it on. The next time anyone on your team types that word, it gets the right pronunciation automatically. From the Glossary page, you can also scope a pronunciation to a specific locale (like British English) or a specific voice if needed.

Note: Pronunciation controls work with all voices, but some are better than others. If you're using a voice where reliability is more limited, you'll see a notice in the pronunciation menu with the option to switch. We're actively expanding support to expressive voices in Spanish, French, and German.

To learn more about how pronunciation controls work, check out our documentation.

Select an element to see quick, relevant actions right on the canvas.

With contextual menus, you can make quick and easy edits right where you’re working instead of switching back and forth between Assistant and the Inspector panel.

What’s new

When you select a layer on the canvas, you’ll now see a contextual menu with quick actions for that element type.

• Access the most common edits without opening other panels
• Reduce context switching (especially if you’re creating with Assistant)
• Stay focused on the canvas while you iterate

This helps editing feel faster and simpler, whether you’re new to Synthesia or polishing a final draft.

Invite anyone to submit a single photo to create a Personal Avatar—no account setup required.

Personal Avatar from Photo Requests are finally here for Enterprise creators! Now you can get the right faces into your videos without onboarding new people to Synthesia.

What’s new

You can invite anyone (even non-users) to create a photo-based Personal Avatar for your workspace.

• Send a request by email (or copy a one-time link)
• The recipient completes a short, guided flow in one session
• Once it’s submitted, the avatar is created and added to your account within minutes

This makes it much faster to get an avatar of a CEO, spokesperson, partner, or subject-matter expert without extra setup or back-and-forth.

Learn more about Personal Avatar requests in our Knowledge Base.

Edit original and translated dubbing transcripts without validation blockers, with audit logging for traceability.

We’ve made it easier for Enterprise creators to correct original and translated dubbing transcripts.

What’s new

You can now more freely edit both original and translated transcripts in your dubbing workflow.

• Fix transcription errors, translation mistakes, and speaker misattributions
• Adjust tone and phrasing to better match how you want the final video to sound
• Keep teams accountable with audit logging of edits

The first time someone edits, they’ll see a one-time reminder to edit responsibly. After that, you can make the corrections you need, without extra friction.

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

Share customizable Avatar outfits and Spaces with your teammates—or your whole workspace.

Today, we’ve introduced Outfit and Space sharing, so teams can reuse customizable avatar Outfits and Spaces without rebuilding them from scratch. Available on Enterprise plans.

How it works

To share it with a specific user, or several users:

• Open up the 3-dot menu and select Share.
• Type the names of the users you'd like to share it with in the Select users field, or click on the dropdown button for that field to find them in a list of workspace users.
• Click the Share button next to the Select users field to share your avatar.

To share it with the entire workspace:

• Open up the 3-dot menu and select Share.
• In the bottom-left of the Share menu, click on the Invite only dropdown.
• Select the Shared with Your Workspace Name option.

The result: faster and more consistent video content creation.

For more details, check out our documentation.

Upload any screen recording (MP4) and Synthesia automatically converts it into a fully editable video.

You can now upload an external screen recording (MP4) directly into the Editor — and we’ll automatically:

• Transcribe the voiceover into an editable script
• Remove filler words
• Split long recordings into structured scenes
• Turn it into a fully editable Synthesia video

Available on all plans.

Why it matters

Bring your own recording from anywhere (QuickTime, Camtasia, OBS, etc.) and save time by instantly converting it into a script-based, structured video. Without having to rebuild everything manually.

This unlocks new workflows: subject matter experts screen record in their preferred tool → then creators refine in Synthesia, teams blocked from using browser extensions can still use the full structured workflow, and legacy training videos can be modernized without re-recording.

In short: you don’t have to start your transcript from scratch anymore when you upload a screen recording – Synthesia automatically transcribes it for you into an editable script.

How to try it

• Open the Editor on an existing Synthesia video
• Select Upload Screen Recording
• Upload your MP4 (up to 500MB, max duration of 30min)
• Review and refine your auto-generated script and scenes

To learn more about today’s release, check out our documentation.

• List videos & retrieve video responses and video.completed webhook payload now includes .srt / .vtt captions download URLs.
• New webhook event "video.failed" has been introduced.
• List videos & retrieve video responses and video.completed webhook payload now includes thumbnail download URL.
• List videos endpoint response will include all videos with at least 1 generated version, regardless of whether or not the current version is a draft.
• List templates endpoint response now includes both custom and stock templates.
• List videos endpoint response now includes videos from both Workspace and My videos.