AI Image and Video Release Notes
Release notes for AI image, text-to-video, image editing, and generative media platforms
Products (14)
Latest AI Image and Video Updates
- July 2026
- No date parsed from source.
- First seen by Releasebot:Jul 15, 2026
Dubbing 2.0 is here: a new model, a new bar for quality
Synthesia releases Dubbing 2.0 with a new lip sync model, more natural voices, and timing-aware translations for more human, high-quality dubbing. Upgraded lip sync is free and on by default across all plans, with improved glossary support and easier transcript and translation editing.
An improved, end-to-end dubbing system with a new state-of-the-art lip sync model, more natural voices, and translations that hold their timing, so your message lands the same in every language.
Today, we're releasing Dubbing 2.0, the biggest leap in dubbing quality since we launched the product.
Dubbing has always involved a trade-off. We're wired to sense when something's off, an unnatural tone, a distracting accent, lip sync that doesn't quite land, and in a business context that lack of authenticity is a real problem. When the goal is to inform and inspire people to act, content that "feels like AI" gets in the way.
So we improved dubbing to make it more human: a new state-of-the-art lip sync model, higher fidelity and more expressive voices, and translations that stay true to the original timing, all while preserving each speaker's original voice and delivery. Upgraded lip sync is now free and on by default, available on every plan.
Why we improved it
Dubbing has always been one of the most powerful ways to bring content to new markets, and AI has made it faster and more accessible than ever. As more teams used it for training, comms, and marketing at real scale, we saw an opportunity to push the quality further, tighter lip sync, more natural and expressive voices, and translations that stay truer to the original, so even more of your first pass is ready to go.
Dubbing 2.0 is that step change: the same workflow you know, now with output that keeps your message's meaning, professionalism, and human connection in every language.
What's new
- A new state-of-the-art lip sync model. Natural, studio-quality lip sync that holds alignment across fast cuts and transitions, and stays matched to the right on-screen speaker even when something briefly passes in front of the mouth.
- More natural, expressive voices. Higher fidelity audio with a wider emotional range and more natural pacing, preserving each speaker's original voice and delivery.
- Translations that keep their timing. Improved translation quality that stays close to the length and rhythm of the original, with Adaptive and Original timing modes to control pacing, so there's less to fix afterwards.
- A Glossary that carries your terminology. Brand names, product names, and acronyms apply automatically at translation time and stay consistent across the workspace, making terminology correction the exception rather than the rule.
- Frictionless transcript and translation editing. Review and refine both the transcript and the translation, and regenerate just the part you changed, with no credits used to review or edit. (Available on Enterprise.)
- From source to every market, faster. Record yourself, or upload any file, and we detect the source language automatically. Export per-language MP4s, WAV audio, or SRT and VTT subtitles, or share a single smart link that serves every viewer their language through one multilingual player.
What's next
This is just the start. We're already expanding our most expressive voices across more languages and pushing improved quality across every locale.
To learn more about how Dubbing 2.0 works, check out our documentation.
Original source - Jul 13, 2026
- Date parsed from source:Jul 13, 2026
- First seen by Releasebot:Jul 13, 2026
Motion Graphics: from script to animated visuals, no design expertise needed
Synthesia introduces Motion Graphics, bringing branded animated infographics, timelines, flows, charts, and custom motion scenes directly into the Editor and Assistant. Powered by its SyRen rendering model, it adds brand-applied templates, editable text, sound effects, and no-design-needed video creation.
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.
Original source All of your release notes in one feed
Join Releasebot and get updates from Synthesia and hundreds of other software products.
- Jul 13, 2026
- Date parsed from source:Jul 13, 2026
- First seen by Releasebot:Jul 13, 2026
Bring sound to your animations
Synthesia adds preset sound effects for entrance and exit animations, making it faster to add polished audio moments.
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.
Original source - July 2026
- No date parsed from source.
- First seen by Releasebot:Jul 13, 2026
Early access: Gemini Omni Flash live in Synthesia
Synthesia now supports Google Gemini Omni Flash in public preview, letting users generate and edit video from text, image, and audio inside the platform. The new model is live on self-serve plans, with Enterprise access coming soon.
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.
Original source - July 2026
- No date parsed from source.
- First seen by Releasebot:Jul 13, 2026
10 improvements to your Editor experience
Synthesia ships small but high-impact Editor improvements that make resizing, trimming, stock video search, and caption restyling smoother and more predictable, with better precision, fewer mis-clicks, and cleaner everyday editing.
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)
- July 2026
- No date parsed from source.
- First seen by Releasebot:Jul 13, 2026
Just say the word: Rebuilt pronunciation controls in Synthesia
Synthesia releases rebuilt pronunciation controls with voice recording, live preview, one-click bulk apply, and a workspace-wide Glossary that works across voices. The update is available on all plans and aims to make pronunciation faster, more consistent, and easier to manage.
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.
Original source - July 2026
- No date parsed from source.
- First seen by Releasebot:Jul 13, 2026
Edit faster with contextual menus
Synthesia adds contextual canvas menus that let users quickly edit selected elements right on the canvas, reducing back-and-forth between Assistant and the Inspector panel and keeping creation faster and simpler.
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.
Original source - July 2026
- No date parsed from source.
- First seen by Releasebot:Jul 13, 2026
Request a Personal Avatar from Photo
Synthesia adds Personal Avatar photo requests for Enterprise creators, letting anyone submit a single photo by email or one-time link to create an avatar without account setup. The feature speeds up getting CEO, spokesperson, partner, or expert avatars into videos.
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.
Original source - July 2026
- No date parsed from source.
- First seen by Releasebot:Jul 13, 2026
Correct dubbing transcripts seamlessly
Synthesia adds freer editing for original and translated dubbing transcripts, removing validation blockers while adding audit logging to help Enterprise creators correct errors and keep edits traceable.
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.
Original source - July 2026
- No date parsed from source.
- First seen by Releasebot:Jul 13, 2026
Share avatar outfits and spaces
Synthesia introduces Outfit and Space sharing, letting teams reuse customizable avatar outfits and Spaces across users or an entire workspace on Enterprise plans for faster, more consistent video creation.
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.
Original source