HeyGen Release Notes

Summary

HeyGen’s June updates include new HyperFrames skills, advanced avatar tools, live avatar APIs, Speech Cleanup, cloud rendering, and deeper integrations across developer workflows.

June was a big month. We hit $200M in ARR, roughly doubling in about eight months. We celebrated for about five minutes. Then we shipped 22 launches. Here's what we built.

The next generation of HyperFrames skills

Skills are pre-built agent workflows. In June we shipped the next generation of HyperFrames skills, focused on workflows, bringing the platform to nine in total:

1. Website to video gives the agent a URL and gets a finished video back. It reads the site's content, structure, and branding and scaffolds a complete video from it.
2. PR to video takes a GitHub pull request and outputs a narrated video walkthrough of the code changes. No one reads changelogs. People watch videos.
3. Beat sync inverts how most video is made. Instead of choosing music and editing to match it manually, you give the agent a song and it analyzes downbeats, swells, and bass drops to design the video around the music. One of our developers described it as getting to "better outputs much, much faster."
4. Captions / video-use handles the full caption pipeline in one instruction: transcription, timing, brand-consistent formatting, and rendering. Captions aren't optional anymore. Most people watch video on mute. This makes captions the default.
5. Launch video takes a product brief (name, features, tone) and produces a finished, publish-ready launch video. Scripting, animation, voiceover, captions, motion all handled.

At the end of June, all nine HyperFrames skills became a unified, intelligent platform. The agent routes automatically based on context. You describe what you need. It goes to the right workflow. This is the shift from "code-based video tool" to "agentic video platform.”

We also added additional capabilities to HyperFrames

• Code Snippets gave the agent a library of pre-built, tested HTML building blocks to pull from. Instead of reinventing animated title cards and data visualizations every time, the agent has proven components ready to assemble. Faster output. More consistent quality.
• Cloud Rendering was the unlock that made HyperFrames production-ready. Before this, rendering required headless Chrome and FFmpeg running locally. Now you push the composition and rendering happens in HeyGen's cloud. That means HyperFrames can live in CI/CD workflows, serverless functions, and scheduled pipelines without anyone's laptop being involved.
• Native music and sfx turned audio from an afterthought into a one-line instruction in the HeyGen CLI. 100,000 background tracks, sound effects, a free tier of tracks, all built in — all free. No external sourcing, no manual integration.

Avatar technology hit new ground

Avatar Look Packs

Look Packs are a new way to create looks for your digital twin that actually look like you. Most AI-generated looks only kind of resemble you, with a slightly different face every time. Look Packs solve that.

Powered by Image N, our new AI image engine built for generating images of people rather than general-purpose scenes, Look Packs give you a polished, persona-based set of consistent looks in one tap. The same person across every outfit, every setting, every context. No more generating one look at a time and hoping it lands. Start with health and wellness, legal, teacher, or fitness, and your twin shows up looking like you every time.

Avatar Realtime API (Broadcast)

This changes what an avatar can be.

Until now, HeyGen avatars were pre-rendered. You write a script, render a video, publish a recording. The Avatar Realtime API makes the avatar a live streaming agent. It can browse the web, see real-time inputs, and respond in the moment. The difference between a voicemail and a phone call.

We demonstrated this by putting an avatar on Twitch 24/7. Viewers sent GitHub repos in chat. The avatar opened them, reviewed the code, and gave live feedback.

Link:

https://developers.heygen.com/avatar-realtime

World's longest talking video: 30 minutes, continuous

HeyGen can now generate 30 minutes of continuous talking-head video in a single pass. That's 6x longer than the previous industry ceiling and 10x our own prior maximum.

The technical achievement isn't just the length. It's the consistency. Most AI video systems drift over time: the face gradually stops looking like you, the voice subtly shifts. Our streaming inference framework stays locked on your likeness and voice for the full 30 minutes.

Full online courses. Employee onboarding modules. Recorded presentations. These are now in scope for AI video. Available on Avatar III, IV, and V, on both API and web.

Link:

https://developers.heygen.com/models

Cinematic Avatar API

Cinematic Avatar API takes a natural language prompt and up to three Avatar Looks, then returns cinematic footage with your real face in it. Your coding agent can call it directly, which makes cinematic video one line in your pipeline instead of a project on your calendar.

Link:

https://developers.heygen.com/cinematic-avatar

New content tool: Speech Cleanup

Record a rough take. Upload it. Speech Cleanup removes every filler word, awkward pause, and false start, then stitches the remaining footage into a single seamless take with no visible jump cuts.

Every other filler removal tool on the market (Descript, CapCut, Submagic, Cleanvoice, Adobe, Riverside) cleans the audio. The fillers disappear from the sound but the video still jumps. Speech Cleanup hides the cut visually. The final video reads as one continuous, unbroken take.

Pricing is transparent: you pay per cut applied. A perfect take gets no charge.

HeyGen is now inside every major developer tool

June was also the month we became native to wherever developers work.

• Claude: HyperFrames became an officially listed MCP connector in Claude. From inside a Claude conversation, ask for a video. Claude calls HyperFrames. No context switching.
• Grok: HyperFrames is also in the Grok connector directory. You can prompt a video from directly inside a Grok conversation.
• Cursor: HeyGen became an officially listed plugin in Cursor's marketplace with three skills bundled together: heygen-avatar, heygen-video, and heygen-translate. They chain automatically. Write a video demo inside your coding environment without switching tools.
• Lovable: Connect it as a personal connector and avatar video becomes a feature of your app, whether it’s for onboarding, product walkthroughs, in-app explainers. You can build an app in an afternoon now. Getting people to understand it is the hard part. Now your app ships with a voice, face, and first impression.

Three major AI platforms in nine days.

Link:

https://developers.heygen.com/mcp/overview

We also launched native LinkedIn publishing: create a video in HeyGen, post it to LinkedIn directly. No download, no re-upload, no friction.

And the HeyGen x Stripe integration extended video into the business layer: paywalled content, video-driven checkout flows, monetized product launches, all automated.

Link:

https://developers.heygen.com/docs/stripe-projects

Also shipped

Customer support agent: Meet your new in-app support agent. Ask it the everyday stuff, like "how do I create my avatar?" or "where do I change the language?", and get an answer in seconds while you're working. No ticket, no waiting, no digging through help docs. And it keeps up as we ship, so the answer is always current.

Questions? Reach out at [email protected] or find us on X @HeyGen.

Original source

Summary

Explore the biggest HeyGen updates from May 2026, including HyperFrames, Avatar V, LiveAvatar, Android, and integrations that make AI video native to your workflows.

May didn't let up. Eighteen features and products shipped, and the story from April only gets louder. Video stopped being something you make and started being something your tools just do.

Your webpage is now a video too, written in the same HTML and rendered a thousand ways in the cloud before standup. Your avatar takes direction, leans in, stays serious, and delivers exactly the way you want. Your Digital Twin holds a live conversation inside the voice agent you're building, in the same face and voice that recorded yesterday's keynote.

Here are the big updates for the month, what each one is, and how to put it to work.

Video the way you code a webpage

HyperFrames turns plain HTML into video. Your agent writes the markup, the markup becomes a finished video, and the skills that already build your webpages now build your videos too. No separate tool, no separate team, no separate budget. In May, that idea grew into a full studio.

• Community hub. Publish your own compositions and remix everyone else's, so you start from real work instead of a blank page.
• HTML in Canvas. Your video can bend, melt, and move through 3D space, which unlocks motion graphics you could not pull off before.
• Texture and shader catalog. Texture-masked text, shader backgrounds, and shader-powered transitions, all installable with one command.
• Live inspector. Tweak any composition in real time, the way you would in a real editor.
• Open-source captions. Fifteen styles you add with a single command, then ask your agent to drop onto your video. Transcription and background removal run locally, with no API keys to manage.
• Templates and variables. Render at scale in the cloud on Lambda, so one composition becomes a thousand with no render farm to babysit.
• Vercel deploy. Spin up your own HyperFrames render API in a few clicks.

The artifact your engineers already know how to build is now the same artifact your video team ships, so the localized campaign that used to need its own software, its own headcount, and its own line item needs none of them.

Try it at hyperframes.heygen.com.

Avatars you direct, not just prompt

Avatar V got three upgrades in May that together turn an avatar from something you prompt into something you direct.

• Avatar V: Custom Motion. Write the performance in plain English. "Look at the camera, lean in, stay serious." "Open hand gestures throughout." "Thumbs up at the end." Face, hands, posture, gaze, and energy are all directable in a sentence, so the same script becomes a measured executive update or a high-energy social cut depending only on how you direct it.
• Avatar V API. The same model is now a clean API call at five cents per second, grounded enough to ship inside a product instead of a demo.
• LiveAvatar integrations. Your Twin can now hold a live, real-time conversation inside whatever you are building.

Put together, that is one identity across three surfaces. Recorded video, live conversation, and a programmatic API, all in the same (or different) face and voice. The avatar that recorded yesterday's keynote can answer customer questions on your support page this morning.

Create your AI avatar at app.heygen.com/avatars.

Video that lives inside the tools you already use

Four integrations and a native app shipped in May. Each one lets you generate a finished video without opening HeyGen.

• Superhuman. Reply to an email thread with an avatar video instead of retyping the same explanation a fourth time.
• Codex. Generate a product demo, tutorial, or feature walkthrough from your editor, with A-roll, B-roll, audio, captions, and motion graphics all callable as you write code. Your product can ship video the same week it ships the feature.
• Canva. Pull an avatar into a slide your team already built, turning a static design into a narrated video on the same canvas.
• Lovable. Add HeyGen as a personal connector over MCP and OAuth, then prompt avatar video straight into the app you are building, so it launches with a face and a voice on day one.

Across all of them, video stops being a separate project on someone's calendar and becomes a step inside the work already in front of you.

HeyGen, now on your Android

The web has been HeyGen's home base. In May, the full app came to Android, so you can record, generate, and share without a laptop. The idea you have on a call, in your car, or while running an errand no longer waits until you are back at your desk. Video becomes something you do on the spot.

Download it on Google Play.

Original source

Summary

Explore HeyGen’s latest updates, including advanced avatars, AI video automation, and new tools that turn prompts, agents, and workflows into fully produced videos.

April was a wild ride. We launched 15 features and products, and when you stack them up, a story takes shape. Video stopped being a tool you open and started being something your tools just do. Your coding agent now ships video. Your podcast now becomes social clips in 175+ languages and dialects while you’re in line for coffee. Your Digital Twin can now walk across a cinematic scene while interacting with up to two other people.

Here’s what shipped, why it matters, and how to play with it this week.

One 15-second clip, unlimited looks and videos

Avatar V is here, and it’s our most advanced avatar model yet. It does something no avatar model has done before: combine the flexibility of photo avatars with the realism of video avatars in a single model.

Here’s the part that feels almost unfair. You record one 15-second clip. From that single take, you get full upper-body movement (waist up, not just face and shoulders), so it actually feels like real studio footage. You get multi-look generation, so you can select different outfits, settings, and styles from one base recording without losing your identity. You also get multi-angle consistency across shots, with no drift and no uncanny valley. And you get long-form stability, so your face, voice, and presence stay locked in even on the longest videos.

If you’re a creator, founder, marketer, or anyone whose face is part of the brand, you’re done with reshoots. Record fifteen seconds of yourself once and get a year of content. Different outfits for different campaigns, different settings for different audiences, but the same on-screen presence everywhere.

Seedance 2.0, now starring you

Seedance 2.0 is the model everyone has been talking about, and HeyGen is the first avatar video platform integrating it with identity-verified human faces. Every other implementation of Seedance is locked to fictional characters. With HeyGen, your real Digital Twin gets cinematic motion, dynamic camera work, and up to three avatars in a single scene.

The more interesting story is where you can actually use it. Seedance 2.0 is now wired into multiple surfaces inside HeyGen, so you can reach for it in whichever workflow already fits how you work.

Inside Avatar Shots

This is the most direct path. Open Avatar Shots, choose Seedance 2.0 as your generation engine, and direct your Digital Twin through cinematic scenes with full body motion and dynamic camera work. Pick the prompt, the scene, the camera move, and Seedance does the rest. If you came here to make a brand film with your face in it, this is the front door.

Inside Video Agent

If you’d rather just describe what you want, hand the brief to Video Agent. Seedance 2.0 is now a first-class engine in the Video Agent creation flow, alongside Avatar V. Give Video Agent a prompt, and it automatically composes the right mix of Seedance cinematic shots and Avatar V scenes into a finished video. You don’t have to step out into Avatar Shots manually or pick the engine yourself. The agent picks it for you.

Across Digital Twin everywhere

The same Digital Twin you built for Avatar V is the one Seedance casts in those cinematic shots. Record once, walk through a coffee shop, gesture across a stage, hand off a line to two other Twins of yourself or your team. One identity, two engines, full coverage from talking head to cinematic scene.

You can now produce the kind of cinematic, story-driven video that used to require a director, a crew, a location, and a week of editing, and you can do it from whatever workflow already fits the job. Direct it yourself in Avatar Shots, or describe it once and let Video Agent compose it for you. Brand films, founder narratives, ad creative with real production value. All from your desk, with your real face, in an afternoon.

Turn one podcast into a hundred clips

Picture this. You recorded a 90-minute podcast on Friday. Then, your editor needs to work six hours to pull clips. By Tuesday, your audience has already moved on.

Instant Highlights v2 kills that problem. Upload any long-form video, whether it’s a podcast, webinar, keynote, interview, or livestream. You get publish-ready short clips for every platform in one workflow.

Type “the part where she talks about fundraising mistakes” and the AI finds the moment inside a 3-hour episode. Face tracking with dynamic camera follow makes a 9-by-16 cutdown of your keynote feel like a real op, framed it instead of a dumb static center crop. Two people on screen get auto-stacked split frame, or speaker cut. Captions, translation into more than 175 languages with lip sync, and 4K upscaling are all baked in. No third-party tools, no extra exports.

If you produce long-form content, this collapses your post-production stack into one upload. The clips ship the same day as the episode. Your audience hears it while it’s still hot, and your global audience hears it in their own language without waiting for a localization vendor.

Now your AI agent can ship video

For everyone building with AI agents right now, there’s a quiet question that nobody answers cleanly. Agents always end at a human, so what’s the last mile? For most teams today, the answer is a wall of markdown. We don’t think that’s the answer. We think the answer is video.

In 12 days, we shipped three things that make that real.

HeyGen CLI wraps our v3 API in a single binary with structured JSON output and a built-in wait flag. You can pass a prompt, and let Video Agent pick the avatar, voice, script, and layout for you. Or you can pass a JSON body and drive every detail yourself. macOS and Linux, no runtime dependencies.

If you’re a developer, you can now generate videos exactly like you run a curl command. Drop it into a build pipeline, a cron job, or a Slack bot. Your product can ship video as easily as it ships email.

HyperFrames is now open source under Apache 2.0. The pitch is wild. You write videos as plain HTML. AI coding agents like Claude Code, Cursor, Codex, and Gemini CLI build them natively. HyperFrames renders the result to MP4. The same input always produces the same output, so it slots right into CI and CD without surprise.

Video is now code. That means version control, code review, automated testing, and reproducible builds for video, the same way you already do for software. For engineering teams, this is the first time video fits inside the workflow you already use to ship everything else.

HeyGen Skills might be our favorite. You’re inside Claude Code or Cursor, and you tell the agent what kind of avatar you want. The agent builds it, selects a voice, writes the script, generates the video, and hands you a share link. Your avatar is saved locally. After that, every video is just one prompt. Try it. It feels like magic.

The friction between “I have an idea” and “I have a finished video” is now one sentence to your coding agent. No tabs, no app switching, no logins. If you live in an IDE, video is now native to your work.

The shared install pattern across all three is npx skills add heygen-com/. Three different surfaces, one consistent way agents reach them.

We open-sourced video

When we open-sourced HyperFrames, we said we wanted it to be the way AI agents and creative teams ship video together. Since then, we’ve been steadily filling in every part of that loop. Today, HyperFrames is a packaged solution that covers the full lifecycle, from idea to render to share.

Here’s what’s now in the box and what each piece unlocks for you.

HyperFrames Timeline. A proper visual timeline editor for HTML-based video. You can scrub through your composition, trim and rearrange scenes, adjust timing, and preview transitions, like you would in any modern video editor. You no longer need to read code to fine-tune a video your agent built. Anyone on your team, technical or not, can polish the final cut.

HyperFrames in Claude Design. A native bridge between Claude’s design surface and the HyperFrames renderer. Designers working in Claude can jump from a static layout into a fully rendered video without leaving the canvas. The handoff between design and motion disappears. The same artifact you used to ship as an image can now ship as a video in the same workflow.

HDR rendering. High dynamic range output is now baked into the renderer, so highlights, shadows, and color depth come through with the same fidelity you’d expect from a premium pipeline. Your videos look broadcast-quality on modern displays, with no extra steps or color-grading workflow.

Canvas editing in Studio. A free-form canvas in HeyGen Studio for visually arranging, editing, and iterating on HyperFrames compositions. You get a flexible, designer-friendly workspace for building video the way you’d build a presentation or a Figma board, with all the power of HyperFrames.

Community discovery. A built-in way to browse, remix, and learn from videos created by people in the HyperFrames community, paired with a celebration of our HyperFrames community milestone. You don’t have to start every project from a blank canvas. Find a composition you love, fork it, and make it your own.

Together, these pieces turn HyperFrames from “a way to write video as code” into a complete production stack. Your AI agent can build the first draft, your team can polish it on the timeline, your designers can finish it in Claude or Studio, the renderer ships broadcast-quality output, and your community helps you find the next idea. One packaged solution covering every step from blank page to published video.

The repo lives on GitHub at heygen-com/hyperframes. The quickstart is at hyperframes.heygen.com/quickstart. There are more than fifty components in the block catalog. If you’re an agent, you’re one npx hyperframes init away from playing.

Video where you already work

The other big April pattern was integrations. The idea is simple. Take a tool people already live in, and make video the natural next step.

The HeyGen and Gamma integration lets you go from a prompt or document to an avatar-narrated presentation video in one place. Drop in PPT, PPTX, or PDF. Get an avatar-narrated video out, fully editable in AI Studio. The Granola integration automatically turns your meeting notes into a recap video.

If you’re a B2B team that lives in decks, meetings, email, or design files, you don’t have to context switch to a new tool to make a video. The deck you already wrote becomes a narrated presentation. The meeting that just ended becomes a recap your team can rewatch. The email you just drafted becomes a personalized video. Video stops being a separate project and just becomes the natural last step of the work you were already doing.

The takeaway

Video has a place in every agent loop now. Whether it’s CLI in your terminal, the IDE you ship from, the podcast file you uploaded, the deck you already wrote, or the meeting that just ended. April put video where the work already is.

May keeps the cadence going. Subscribe to our changelog, or run npx skills add heygen-com/hyperframes and start building. We can’t wait to see what you make.

Original source

Summary

February’s HeyGen updates introduce a redesigned homepage, one-tap social video editing on iOS, ChatGPT video creation, and the new Video Agent API for prompt-to-video workflows.

Video creation has always had a tax on it. You have an idea, but then you have to write a script, find visuals, animate an avatar, and edit it all together. It’s a process stuck in the past. We've been eliminating that tax one feature at a time, and last month we took four big swings.

A redesigned homepage that gets out of your way

HeyGen has grown a lot, and the old homepage was starting to show it. Finding what you needed took too many clicks.

With clearer navigation and dedicated spaces for different creation paths, you can quickly create new videos, manage your avatars, or manage and edit existing content immediately. Less clicking, more creating. The updated Home experience offers greater flexibility while maintaining simplicity, organization, and readiness to support future tools.

Discover the new homepage

Turn videos into social-ready content in seconds

Stop spending hours styling shots, timing captions, and trimming clips. Our new Edit Styles on the HeyGen iOS app turns your raw avatar footage into a polished, social-ready video with a single tap. With 12 built-in templates, it automatically adds word-synced captions, pulls out visual hooks from your script, and applies dynamic zoom effects. You can even customize colors and caption styles. No more manual editing: just shoot, tap, and post. Android support is coming soon.

Download the mobile app

Create videos directly inside ChatGPT

You can now generate a fully produced video without leaving ChatGPT. Powered by HeyGen’s Video Agent, the integration enables users to go from a prompt, script, or idea to a fully produced video directly within ChatGPT. Just describe the video you want, and the agent will handle everything from scripting and visuals to avatar animation and editing. You can refine the video in a chat conversation until it’s perfect. It’s a new way to work. Product demos, training videos, social content, personalized outreach. All of it, from a single prompt.

Try the integration

Video Agent API + HeyGen Skills: One prompt video

The Video Agent API is now live, and we’ve built a HeyGen Skills to go with it. You can use the Video Agent API directly or integrate it with Claude Code via HeyGen Skills.

Simply install the skill, add your API key, and tell Claude what you want. It automatically optimizes your prompt, calls the API, and delivers a finished video. No web app, no timeline, no manual steps.

“One prompt away” means exactly that. Daily market recaps, weekly content summaries, product demos triggered by any workflow—video is now just another output of any Claude Code task. And if you want to tweak it, your session remains accessible in HeyGen whenever you need it.

Learn more

Looking ahead

February’s updates simplify how teams create, edit, and share video at scale. Be on the lookout for more integrations and new features in March.

Original source

Summary

HeyGen is overhauling how credits work based on user feedback that the system was confusing. The key changes: "Generative Credits" are now called "Premium Credits," features that cost credits are clearly labeled "Premium" throughout the product, users see upfront cost estimates before generating, and the platform suggests credit-free alternatives when you're running low. Audio dubbing is now unlimited (no longer costs credits). Premium features include Avatar IV, Video Translation with lip-sync, Video Agent, AI-generated avatar looks, and B-roll from Sora 2/Veo 3.1. Core features like Avatar III, Audio Dubbing, Video Agent Essential mode, and stock content remain unlimited for paid users. The long-term goal is to move more features from premium to unlimited as model efficiency improves.

We heard your feedback: it's not clear which features use credits, and how many credits actions will consume. At HeyGen, we believe AI video generation should empower everyone to bring their ideas to life. We took a step towards that with generative credits late last year.

Today, we're making credits and premium usage even more clear and accessible.

What we heard

Many of you have told us the feature and credit system is confusing. You shared stories of using credits while testing features, and finding it difficult to tell which features cost you credits and which did not. In our own experiments, we validated that confusion, and are now addressing it.

Why premium credits

AI video generation looks very different today than it did when we first launched in 2022. Premium credits help us sustainably deliver cutting-edge, compute-intensive AI models without charging separately for each new feature. They allow us to continuously improve and add capabilities (like Video Agent and Sora 2 integration) while keeping your base subscription predictable. But we need to make this system much clearer.

The changes we're making

1. Clear premium labeling

Features that consume credits are now marked as "Premium" throughout the product. No more guessing which features will use credits.

Premium features include:

• Avatar IV
• Video Translation with lip-sync
• Video Agent
• AI-generated avatar looks
• B-roll generation with Sora 2, Veo 3.1, and other third-party models

2. "Generative Credits" → "Premium Credits"

We renamed "Generative Credits" to "Premium Credits" to make the connection clearer: premium features use premium credits.

3. Upfront cost estimates

Before you generate, you will see how many credits an action will use: "This will use 50 premium credits (200 remaining)." You can make informed decisions before committing.

4. More choice. More control.

When you're running low on credits, we will suggest alternatives that don't consume premium credits, such as:

• "Use Avatar III instead of Avatar IV"
• "Switch to Video Agent Essential mode when premium usage runs out"

5. Audio translation is now unlimited

Good news: video translations with audio overlay (audio dubbing) no longer consume credits.

As we continue to improve model efficiency, our goal is to move features from premium to unlimited whenever possible, expanding what's available to paid users without credit limitations.

Features included in your plan

These features do not consume premium credits and are unlimited for all paid users:

• Avatar III — Create as many videos as you need with our core avatar model, works with your personal photo or video avatars
• Audio Dubbing — Translate videos with audio overlay, unlimited usage
• Video Agent Essential mode — Basic video generation from prompts
• Stock avatar looks — Use any pre-made avatar appearance
• Stock images and videos — Access our full library of stock content

Try it now

Log into HeyGen and start creating. You'll see the new Premium labels, cost estimates, and unlimited alternatives throughout the platform.

Have feedback?

We're listening. Share your thoughts at [email protected], our change log, or our community forum. We read everything.

Original source

Summary

Introducing Avatar V, HeyGen’s most advanced AI avatar model. It delivers unmatched realism and identity consistency. Create studio-quality videos from a simple 15-second recording with lifelike motion, multi-angle stability, and long-form performance.

Every few months, a new AI model ships with a bold claim about realism. The demos look impressive, the side-by-side comparisons are compelling, and the launch post makes it sound like everything before it was a rough draft. Then you actually use it, and that familiar feeling sets in: the slight uncanny quality, the face that drifts, the avatar that starts as you and quietly stops being you twenty seconds in.

We've seen this too. We built around it.

Today, we're introducing Avatar V, HeyGen's most advanced AI avatar model and the most realistic in the world.

What is Avatar V?

Avatar V is HeyGen's next-generation avatar model and the foundation everything else in HeyGen runs on now.

Most avatar systems optimize for a single impressive moment: the screenshot, the short clip, the controlled demo environment where everything is working in the model's favor. They look great in two seconds and fall apart in twenty. Avatar V was built to do something harder.

It was built to hold.

What that means in practice is that one short recording from you generates studio-quality video that maintains your face, your voice, and your presence across angles, looks, and runtime. Not just for the opening shot, but for the whole thing, from the first frame to the last.

We've been training avatar models for years and going deep on the specific problem of human identity in video: the micro-expressions, the natural movement, the quality threshold that separates a good talking head from footage that could genuinely pass as real. Avatar V is the result of that work compounding over time.

Why it’s the best model

The AI video market has a quality problem that most people describe wrong. They say the output looks AI, but what they actually mean is it doesn't look like the person it's supposed to be.

Identity drift is the real problem.

An avatar that starts as you and slowly stops being you. A face that holds in static shots but breaks under motion. A model that generates one great look but can't give you another without becoming someone else in the process. These aren't edge cases. They're the norm.

Avatar V solves identity consistency at the model level, not as a post-processing patch applied after the fact. We trained it specifically on the hard cases: multi-angle footage, long-form content, varied looks generated from a single input recording. The result is an avatar that stays true to who you are across every variable we could throw at it.

Plus, companies like Synthesia still requires studio time to get anywhere close to this output quality. HeyGen does not. Rated number one for most realistic avatars on G2, Avatar V makes that claim stronger than it's ever been.

How it works

Record a 15-second clip

That's the input. Fifteen seconds, no professional camera setup, no studio lighting, no crew required. You need a phone and a few seconds of your time.

From that reference clip, Avatar V builds a complete model of your identity, not just what you look like in one frame, but how you move, how your face settles naturally, and what makes you recognizably you across different contexts. Everything it generates afterward comes from that foundation, which is what makes the output so consistent.

That gap between what goes in and what comes out is exactly where Avatar V does its work.

Multi-angle consistency

Real video isn't a single locked-off shot. It moves, it cuts, and the camera finds you from different positions and angles, and if the avatar can't hold up across that motion, the entire thing falls apart immediately.

Avatar V holds. Your avatar maintains consistency across different shots and angles without drift, without inconsistency, and without the uncanny valley breaking through at the worst possible moment. The face that appears at the top of your video is the same face that appears at the bottom, from any angle the output requires.

This is genuinely difficult to do well. Most models treat each frame as an isolated generation problem. Avatar V treats your identity as a constant and builds outward from there.

Multi-look generation

Every video you've ever recorded came with baggage you didn't choose. The outfit you happened to be wearing that day. The background behind you. The lighting in the room. If you wanted to look different, the answer was always the same: go record again.

Avatar V changes that entirely.

With Avatar IV, what you recorded was what you got. The performance and the appearance were locked together. Avatar V is the first model to separate them.

You record yourself once, naturally. Avatar V captures your real movements, your real expressions, and the specific way you carry yourself when you're actually talking. That performance becomes the foundation. Then you choose how you appear: a different outfit, a different setting, a different version of yourself entirely. Your motion stays real. Everything else is yours to decide.

This matters for real work. You might want one look for a sales video, another for a company-wide announcement, and another for a product walkthrough. With Avatar V, you don't film three separate times to get three distinct results. You record once and choose from there.

Long-form stability

Short clips are easy. Long-form is where most avatar models quietly fall apart.

Avatar V maintains your identity across your longest videos, delivering the same face, the same voice, and the same presence from the first second to the last without degradation or drift. No moment where the avatar stops looking like you and starts looking like a close approximation of someone adjacent to you.

This is the capability that makes Avatar V genuinely useful for the content that matters most: full training modules, product walkthroughs, onboarding videos, and the kinds of recordings that used to require a camera crew and a full studio day to produce.

Pair it with Seedance 2.0

Avatar V handles the message. Seedance 2.0 earns the watch.

Once you have your Avatar V recording, it becomes the foundation for a scroll-stopping video when paired with Seedance 2.0. Avatar V delivers your message with the stable, long-form presence that professional video requires. Seedance generates the cinematic hooks and motion-first scenes that pull people in before you say a word. They cover opposite ends of the same video: the opening that demands attention and the body that holds it.

Most people think about the hook and the message as separate production problems. With Avatar V and Seedance 2.0, they both start from the same 15-second clip. You record once to create cinematic videos starring you.

What comes next

Video is the highest-trust medium for human communication, and when it works, it works better than anything else. When it looks fake, trust collapses immediately and there's no recovering it.

Avatar V was built on a single belief: the output has to be good enough that you'd be willing to put your name on it. Not good for AI. Just good.

We think we're there.

Try Avatar V today

Original source

Summary

HeyGen’s March updates focus on making AI video creation feel truly yours by improving branding speed, adding interactivity, enhancing quality, and expanding tools for builders.

Every tool eventually hits the same wall. It can do the thing, but making the thing feel like yours takes extra work. Your brand colors, your style, your level of polish. March was about closing that gap. We shipped seven updates that make HeyGen videos look better, feel more on-brand, and reach more developers out of the box.

Brand Systems: One URL, every asset on brand

Paste your company's website URL and HeyGen extracts your logo, typography, and color palette automatically. That's your Brand System. It works across Templates, AI Studio, and Video Agent.

In Templates, you apply your brand with a single click. In AI Studio, elements default to your brand fonts and colors. In Video Agent, you can prompt it to use your Brand System and it generates motion graphics that actually match your identity. Set it up once and stop manually adjusting colors on every project.

This is the kind of thing that sounds simple but changes your workflow. No more eyedropping hex codes from your website or hunting for the right font file. Your brand just shows up.

Interactive video experiences

Static video is a one-way street. Interactive Video turns it into a conversation. You can now add in-video quizzes for real-time knowledge checks, branching paths for choose-your-own-adventure scenarios, and CTA buttons that link externally or jump between chapters.

This is a big deal for training and education teams. Build a compliance module where learners make decisions and see consequences. Create onboarding flows that adapt based on role. The branching logic means one video can serve multiple paths without duplicating content.

It also exports to SCORM, so it plugs directly into your existing LMS. Available on Business and Enterprise plans.

Styles for Video Agent

Video Agent can now generate videos in over 100 curated visual styles. Before you generate, pick a style that controls typography, font pairings, color systems, motion pacing, transitions, animation timing, and layout composition.

The same script with the same avatar produces a completely different video depending on which style you choose. A product demo can feel polished and corporate or bold and editorial without changing a single word of the prompt. This makes Video Agent dramatically more flexible for teams producing content across different brands, campaigns, or audiences.

4K video enhancement

You can now upscale any video to 4K, powered by Topaz Starlight Precise 2.5. There are two engines: Standard is faster and uses fewer credits, while Precise delivers sharper results for when quality matters most.

Beyond resolution, you also get frame interpolation that takes footage from 24fps up to 120fps. Find it under the Apps tab as "Upscale Video." Available on all plans with credits.

If you've been sitting on older content that looks dated at lower resolutions, this is the fastest way to bring it up to standard.

Enterprise admin controls

Enterprise teams now have granular control over who can do what. Admins can manage public invite links, sub-workspace access, and default sharing permissions. Video distribution controls let you restrict downloads, public publishing, and social sharing at the org level.

Feature-level settings go further: restrict custom avatar creation, AI-generated avatars, public avatar availability, and Brand Kit creation. The Members tab now supports search, active/pending filtering, and exportable status lists. Sub-workspace management got a refreshed UI with cleaner billing setup and pagination.

All changes apply going forward without affecting existing content. Enterprise plan only.

For builders: Pay-as-you-go API, fal, and MCP

Three updates for developers this month. First, API access no longer requires a subscription. You can top up starting at $5 with straightforward USD-per-unit pricing across all API features.

Optional auto-reload keeps things running without manual intervention. If you're already subscribed, your existing discounts stay intact.

Second, HeyGen's core capabilities are now available on fal's, replicate, runware developer platform. That includes Video Agent, Image-to-Video, Translate (both Precision and Speed modes), and Digital Twin with Avatar 3 and Avatar 4. If you're already building on fal, you can add AI video generation without switching platforms or managing a separate integration.

Lastly, HeyGen MCP is available on Claude, Manus, and OpenAI — you can generate videos directly on these platforms.

Looking ahead

That's seven major updates in one month, and we're just getting started. Seedance 2.0 and Gamma went live last week. April's going to be fun.

Original source

Summary

This month, we're raising the bar on avatar realism, creative control, and global reach. With HeyGen now on Android, a smarter video translation engine, major upgrades to our latest avatar model (Avatar IV), and a refreshed AI Studio experience, you can produce polished, professional content even faster, whether you're scaling training, creating courses, or building your brand through video.

What’s new

HeyGen is now on Android

HeyGen is officially available on Android in the U.S. Create, edit, and publish videos directly from your phone, regardless of device.

For course creators, coaches, and anyone who needs to move fast, the Android app puts full video creation in your pocket. Capture ideas on the go, make quick edits between meetings, or publish content without ever opening your laptop.

U.S. Android user? Get started here.

Translate videos with speed and precision

We've redesigned how video translation works with two distinct engines built for different use cases.

Speed Mode provides fast, reliable translation in 175+ languages, accents, and dialects. It's optimized for quick turnaround, making it perfect for daily social posts, quick updates, or any content where you need to move fast. Speed Mode handles sentence-level translation with light alignment and solid lip-sync.

Precision Mode is our best-in-class translation engine, built for when accuracy matters most. It's video-aware: better occlusion handling, better multi-speaker support, context-integrated translation that's character-sensitive and timing-aware. The result is truly lifelike lip-sync and natural voice output, even for movement-heavy content. Ideal for courses, tutorials, product demos, and client deliverables.

If you're scaling content globally, you now have clear options: Speed when you need volume, Precision when you need polish.

Learn more about translating with Heygen.

Create more natural, controllable avatars with Avatar IV upgrades

Our SOTA avatar engine just got more powerful.

More natural movements

Control when gestures happen and in what sequence: prompt for a wave at the beginning, then natural movement as your avatar speaks. Your avatars finally move the way a real person would: purposefully, not on a loop.

Better control

With better expression controls, your avatars now display subtler, more realistic expressions and body language, the kind of micro-movements that make the difference between "AI video" and "professional video."

Intelligent render selection

We've simplified how rendering works. Avatar IV automatically uses the best rendering approach for your video. No more fretting over which mode to pick. When you add custom motion prompts, the system routes to our higher-fidelity engine under the hood. When you don't, you get our most stable, consistent output by default. Less guesswork, better results.

And AI Studio updates for all

We've redesigned the AI Studio to eliminate friction and give you more creative control without leaving the editor.

Style your avatar without leaving the studio

Generate looks directly inside Studio, including outfits, styles, or visual treatments for your avatar without switching to the Avatar tab. Need a blazer for a pitch or something casual for a course? Switch looks in seconds without breaking your flow.

Your avatar, anywhere

Place your avatar in any environment instantly with custom Avatar Backgrounds. Swap backgrounds for solid colors, stock photos, AI-generated scenes, or your own custom uploads. Every background works seamlessly with all avatar framings: Full, Circle, or Close-up.

A faster, cleaner editing experience

Our fully redesigned Studio layout feels faster, cleaner, and easier to work in, especially for creators who spend hours editing.

Enjoy smoother interactions across long editing sessions, faster response times when adjusting parameters, and a cleaner interface that consolidates essential controls.

We've also overhauled the context menu, replacing More Options with a unified Properties panel. Edit any element, such as text, image, and shape, from one consistent menu, and access interactivity controls without digging through submenus.

What’s leaving

At HeyGen, we live for customer feedback. Our users shape who we are, what we build, and sometimes, what we remove. To enhance the user experience, please note the following changes we’ve made to the platform:

Voice Tab relocation

The standalone Voices tab has been relocated for your workspace. Nothing has been removed, your Voice tools now live in the workflows where they’re used most:

• AI Studio: Sidebar → Voice → Create / Integrate
• Proofread Studio: Voice dropdown → Track Voices
• Avatars: Voice setup for Avatar creation

Flux product placement removal

Flux product placement (Assets) are now removed as an editing option. Don’t worry:

• Your existing Flux Looks with product placement will remain untouched
• You can download and reuse anything you've already created but
• New Looks made with Flux won't include the product placement feature

While Flux product placement was valuable for specific use cases, HeyGen will rely on Nanobanana exclusively for Look edits using reference images. This means product placement will now be entirely handled through the Edit existing look option, ensuring superior results.

Media Tab removal

This feature was removed as part of our simplification efforts. Users did not find it helpful, and thus it was deprecated.

Questions? If this change impacts your workflow, our support team can help you explore options or talk through alternatives.

Looking ahead

The holidays are just around the corner, but for HeyGen customers, Christmas always comes early. Introducing (even more) avatars from HeyGen!

We release new avatars and looks every week! Be sure to regularly check the Avatars tab for even more ways to tell your story.

Sign up for free here

Original source

Bring real conversations to life with LiveAvatar

HeyGen’s October 2025 release redefines interactive storytelling with lifelike LiveAvatars, cinematic Veo 3.1 and Sora 2 integrations, and powerful new learning tools.

This month, we’re taking storytelling and interactivity to the next level with new integrations, intelligent learning features, and lifelike avatars. From cinematic B-roll powered by Sora 2 and Veo 3.1 to interactive quizzes and LiveAvatar, these updates enable more dynamic, personal, and engaging video communication.

We’re excited to introduce LiveAvatar by HeyGen, offering hyper-realistic, real-time interactive avatars that enable face-to-face human conversation experiences on demand, and at scale. You can create your own avatar with just two minutes of footage or choose from diverse presets to instantly bring realism and personality to customer support, coaching, or education experiences. Already used by visionaries like Reid AI, Coursera, HP, Bosch, and Proto Hologram, LiveAvatar combines authenticity, responsiveness, and enterprise reliability to bring a new level of human touch to AI-powered communication.

Add integrations for next-level video communication

We’re bringing cinematic power directly into your creative workflow. New Veo 3.1 and OpenAI Sora 2 integrations give you complete control over avatars, visuals, and storytelling in HeyGen.

Veo 3.1

The Veo 3.1 integration gives creators full control over every voice, character, and scene. Generate once in Veo and keep your avatar consistent across shots, preserving your real voice, true look, and seamless motion. Perfect for dynamic action, scroll-stopping hooks, and multi-speaker avatar videos, you can use your existing avatar or start from a photo for future use. Upload up to three images per scene to add people, products, or environments mid-story.

OpenAI Sora 2

OpenAI Sora 2 is now fully integrated into HeyGen. Bring cinematic-quality video generation directly into your creative workflow. With Sora 2, you can instantly generate B-roll, scenes, and dynamic visuals from a simple prompt without switching tools, exporting files, or juggling software. This integration unlocks new levels of creativity and speed for creators, educators, and businesses alike, making it easier than ever to turn ideas into polished, professional video content.

Make interactive learning even easier

HeyGen’s Learning & Development Solution is now more powerful and interactive, enabling teams to create personalized, trackable learning experiences that keep learners engaged.

Add quizzes to videos

With built-in quiz features, L&D teams can reinforce key concepts, measure learner comprehension, and keep training sessions interactive from start to finish. By embedding quizzes directly into videos, you transform passive lessons into engaging learning experiences, turning viewers into active participants who retain more through real-time understanding checks.

Improved interactivity UI

HeyGen’s new interactivity layout makes it easier than ever to add and manage engagement features within your videos. The redesigned UI gives creators a clear, visual way to locate and insert branching paths, quizzes, and embedded links directly in the timeline.

Multilingual player support for SCORM export

The multilingual player now supports SCORM export, enabling the delivery of localized training at scale. With this update, L&D teams can share all translated videos through a single link that integrates directly into their LMS, allowing learners to access and complete training in the language of their choice within a fully trackable, SCORM-compliant experience.

Looking ahead

This month’s releases strengthen how teams create, communicate, and teach with video. With LiveAvatar, Veo 3.1, and Sora 2 integrations, as well as new interactive and multilingual training tools, HeyGen empowers every team to create content that’s more engaging, adaptable, and globally accessible.

Sign up for free here

Original source

Summary

This month’s updates include the public launch of Video Agent, new creative tools in AI Studio, multilingual playback, and LMS integration, making it faster and easier than ever to create, scale, and share professional videos.

This month, we’re introducing some of our biggest updates yet, including the public launch of Video Agent, powerful new creative tools in AI Studio, multilingual video playback, and LMS integration. These features are designed to help you create, scale, and share professional videos faster and more seamlessly than ever.

Generate a professional video from a simple prompt

We’re excited to announce the public release of Video Agent, the world’s first creative operating system for video. With just a single prompt, Video Agent handles the entire production workflow—scripting, visuals, voiceovers, avatars, editing, and delivery. It automatically builds a narrative, selects the right assets, syncs voiceovers with AI avatars, applies editing effects, and produces a final, ready-to-use video. Plus, with support for localization in over 175 languages and dialects, it’s built to scale content creation for global audiences.

The real value of Video Agent is in its speed and simplicity. What once took days or weeks can now be done in minutes, dramatically reducing costs and complexity for creators, marketers, and educators. By making video creation more consistent and brand-aligned, it lowers the barriers for anyone without professional production skills.

New tools for global training at scale

To support enterprises and L&D teams delivering training worldwide, we’re introducing new features that make HeyGen videos easier to integrate and share across platforms and languages.

LMS integration

L&D teams can now seamlessly scale training with support for learning management system (LMS) integration. Import HeyGen videos and courses directly into your LMS with just a few clicks. Simply open a project, select a generated video, click share, and choose LMS to get a ready-to-use link. This integration ensures that AI-powered training content fits into existing workflows, providing employees and learners with direct access to engaging, localized videos where they already learn.

Multi-lingual video player

We’re excited to introduce the multi-lingual player, a powerful new way to share translated content at scale. Instead of juggling multiple links, all your translated videos now live in a single, shareable link with a simple dropdown that lets viewers switch between languages for both audio and captions. Fully compatible with avatar and standard translated videos—including batch translations—the multi-lingual player ensures your audience can engage with your content in the language they know best, making training, marketing, and communications more accessible worldwide.

Make every video stand out with instant B-roll

To give creators even more flexibility and control, we’ve added powerful new tools for visual generation and caption customization inside AI Studio.

New AI tab in the editor

We added a new AI tab in AI Studio, designed to make image and video generation more seamless than ever. With support for Nano Banana and Flux Kontext, the update puts visual creation front and center, enabling high-quality B-roll generation directly in HeyGen. With support for image-to-image editing in this release cycle, it’s easier to enhance or adapt visuals, drop them into your canvas, and instantly level up your video projects without leaving AI Studio.

Caption customization

We’ve expanded creative control with 15 new caption styles and full font customization, making it easier to match your video’s tone, whether professional, playful, or cinematic. You can now upload and use your brand’s exact fonts for a consistent look across all content with no extra steps required.

Looking ahead

Together, these September updates mark a major leap forward in making HeyGen faster, smarter, and more global. From the launch of Video Agent to new AI-powered creative tools, caption customization, multilingual playback, and LMS integration, we’re building a platform that empowers creators, marketers, and L&D teams to scale video like never before.

Not a user yet?

Sign up for free here.

Original source

HeyGen’s August 2025 release introduces more realistic full-body avatars, enhanced voice design, flexible creation modes, and expanded enterprise and API capabilities for scalable, personalized video content.

Users now have greater flexibility in designing and personalizing avatars and voices. Lifelike digital twins, customizable voice prompts, and new options for speed or quality enable fine-tuning for truly unique content.

Full control of how your avatars look and sound

Users now have greater flexibility in designing and personalizing their avatars and voices. From lifelike full-body Digital Twins to customizable voice prompts and new options for speed or quality in avatar creation, these updates provide users with more ways to fine-tune their content and make it truly their own.

Digital Twin is now powered by Avatar IV

HeyGen’s new Digital Twin, powered by Avatar IV, takes personalization and realism to an entirely new level. Built with the world’s leading avatar model, the technology enables users to create a version of themselves that doesn’t just talk, but also moves, gestures, and emotes in ways that feel unmistakably real. From every blink to every tonal shift, the digital twin mirrors its human counterpart with striking authenticity.

What sets this release apart is how immersive and complete the experience is. Digital Twin now represents your full body presence, not just your upper frame, and offers the flexibility of clean or dynamic backgrounds. With Avatar IV, the result is more than realistic footage; it’s recognizable and deeply personal, enabling avatars that don’t just sound like you but feel like you. By combining hyper-realism with adaptability, HeyGen’s Digital Twin redefines what it means to maintain a human presence in digital communication, offering creators the most personal experience the platform has ever built.

Improved voice design

HeyGen is enhancing the voice design experience by updating the modal to display the auto-populated prompt and give users the ability to customize it. Voice design now supports more descriptive prompts beyond age, gender, and ethnicity. This update provides both transparency and flexibility. Users will see the generated prompt, preview voices, and have the option to edit the prompt and regenerate new voices tailored to their needs.

Avatar IV speed and quality modes

HeyGen has introduced the option to choose between higher quality or faster creation when creating an avatar in Avatar IV. With the new update, users can now select a “Max Quality” mode for more detailed results or a “Faster” mode for quicker turnaround, depending on their needs. This flexibility is available across Avatar IV, AI Studio, and quick avatar video creation.

Expanded enterprise and API capabilities

HeyGen is evolving with new capabilities designed to meet the needs of enterprises. From expanded customization and workflow integrations to stronger admin controls, these updates make it easier for organizations to create content at scale, streamline collaboration, and maintain clear oversight across teams.

Template API support

AI Studio is now compatible with template and video creation through our API, giving teams greater flexibility and control. It introduces expanded customization options for variables, including avatars, text, and elements such as frames, icons, images, and videos. Even the script of a scene can be set as a variable and customized via the API, allowing for more dynamic and tailored video generation.

Support for Google Slides

Support for Google Slides has been added to editable templates, expanding beyond the existing PowerPoint integration. Users can now import their Google Slides directly into HeyGen, making it simple to transform presentations into engaging videos. This is especially useful for training content, where teams can quickly repurpose slide decks into video lessons without extra formatting or setup, streamlining the entire content creation process.

Export usage history by product

Admins now have the capability to export usage history by product directly from settings. Previously, only the full audit log could be downloaded, but this update makes it easier to access and analyze product-specific usage data. This is especially important for admins who need clear visibility into how different teams are using HeyGen, enabling better reporting, compliance tracking, and resource management.

Looking ahead

Together, these August updates are a major step forward in making HeyGen more powerful, customizable, and enterprise-ready. By combining hyper-realistic avatars, smarter voice tools, flexible quality modes, and stronger admin and API capabilities, HeyGen empowers both individuals and organizations to create with more precision and efficiency.

Not a user yet?

Sign up for free here.

Original source

Summary

Avatar IV API lets you generate lifelike talking videos from any photo, with clean lip-sync, expressive facial motion, and natural gestures.

Earlier this summer, we launched Avatar IV, our most advanced image-to-video model ever, in the HeyGen web app. Today, I’m excited to share that Avatar IV is now available via API, allowing you to embed it directly into your product experiences.

What’s new: Avatar IV, programmatic

With the Avatar IV API, a photo and a script are all you need to generate a realistic talking video, featuring all the HeyGen magic: accurate lip-sync, expressive facial movement, and even authentic hand gestures. Now you can trigger that exact flow with our API inside your app or workflow.

Under the hood, Avatar IV supports angled or profile photos and works across lifelike or stylized characters (humans, anime, and even pets). It’s built to handle real-world inputs while maintaining natural timing and motion.

Why partners are excited

• Frictionless creation from a photo. Let users start with an existing image (or a generated one) and produce a studio-quality avatar performance from just a script. No cameras. No shoots. Seconds, not days.
• More expressive, more engaging. Avatar IV syncs voice with emotion and powers gesture-aware motion, making every message land with clarity and charisma.
• Flexible by design. Works with front-facing, angled, or profile images; supports lifelike and stylized outputs for on-brand experiences across education, CX, marketing, internal comms, and more.
• Built for developers and product teams. Spin up jobs with a simple POST to our video generation endpoints; use photo-avatar endpoints when you want to programmatically add motion and sound effects or manage avatar assets at scale.

Here’s an example Avatar IV video to show the model’s realism and gesture quality.

Common partner use cases

• Learning and development (L&D), and Education: Turn slide thumbnails or instructor headshots into narrated modules and localize at scale.
• Sales and CX platforms: Auto-generate personalized explainers from a CRM record and just a photo of yourself, to help build personal relationships with your audience with video.
• Creative & marketing tools: Provide users with an “instant host” for product demos, social content, or ads, without needing to book talent.

Plans and availability

Avatar IV API is self-serve on our Pro and Scale tiers, with Enterprise available for custom rates and high-volume usage. You can find the Avatar IV API documentation here.

A note on quality and control

We purpose-built Avatar IV to feel and look natural in real product UX, with clean lip-sync, nuanced facial dynamics, and gesture timing that follows the script. It also pairs beautifully with our voice tools for delivery control, so content sounds as intentional as it looks.

Get started with Avatar IV today.

Original source

HeyGen’s July 2025 release introduces powerful new features like screen recording, generative B-roll, and expressive voice tools to help enterprise teams create high-quality video content at scale.

This month, we’re releasing a suite of enhancements that give enterprise teams more power, flexibility, and creative control to produce video at scale. From integrated screen recording and expanded PPT/PDF editing to premium motion elements, expressive voice models, and generative B-roll, these updates streamline complex workflows while elevating video quality.

Whether your teams are building training programs, customer communications, or global marketing campaigns, HeyGen’s July updates help you work faster, collaborate more effectively, and deliver content that connects.

Expanding capabilities to meet enterprise content demands

Creating training, education, and marketing content at scale requires tools that simplify complex workflows. Our latest releases bring powerful enhancements to screen recording, voice testing, and presentation editing.

Screen recorder in AI Studio

Responding to strong demand from enterprises, we integrated our native screen recorder directly into the AI Studio text editor. You can now capture your screen—with optional mic audio—and instantly create a new scene with synced blocks, all without leaving AI Studio.

This feature is particularly valuable for training, enablement, and product education workflows, enabling teams to produce tutorial-style content faster and with fewer steps.

Editable PPT/PDF improvements

We expanded support for editable PowerPoint and PDF imports by raising the slide limit from 15 to 50 slides. You can now work with larger, more complex presentations while maintaining full editability in AI Studio. This improvement is particularly beneficial for training, corporate comms, and product marketing teams managing high-volume slide decks.

Side-by-side video testing

Side-by-side TTS (text-to-speech) testing is now live in AI Studio, enabling you and your team to directly compare voice engines within the same language and select the best fit for global audiences. Upcoming enhancements will also automatically correct suboptimal engine selections, ensuring even higher voice quality.

Enhance storytelling with seamless visuals and expressive audio

Our latest updates empower your teams to create videos that look and sound more polished than ever. We’ve introduced tools that elevate both the visual and voice experience, making it easier to create B-roll, deliver seamless transitions, dynamic motion elements, and expressive narration for more engaging storytelling at scale.

Generate B-roll with Veo 3 and Seedance 1.0

We’ve expanded HeyGen’s creative toolkit with support for Veo 3 and Seedance 1.0, enabling your team to generate high-quality B-roll directly within the platform. This eliminates the need to source supplemental footage externally, streamlining production while maintaining a consistent visual style. Advanced generative video models in HeyGen let you enrich storytelling, add variety to training and marketing content, and produce more engaging videos at scale.

Magic Match transitions

Our Magic Match transition feature automatically animates matching elements between scenes, eliminating jarring cuts and ensuring a fluid, professional-grade flow from start to finish. By intelligently connecting visuals, it delivers seamless scene-to-scene continuity that enhances storytelling and gives your content a polished, dynamic feel.

Premium motion elements

You can already enhance your videos by adding customizable elements such as text, speed, and zoom effects, making it easier to create engaging and professional content. We’re adding 12 new premium motion elements, including intros, speaker cards, quotes, headlines, and typewriter effects, giving creators everything they need to produce high-quality videos from start to finish without needing to use different tools.

Integration with Eleven v3

We’ve made significant progress in delivering more natural, expressive, and precise voice experiences. We’ve added integration for Eleven v3, ElevenLabs’ most expressive text-to-speech model, giving you greater control over expressiveness. We also added language-specific defaults to ensure the voice panel aligns automatically with the user’s chosen language, streamlining workflows for global enterprise teams.

Streamlined access control for seamless collaboration

Managing users and collaboration at scale requires simple, reliable tools. Our latest updates introduce new permissioning functionality and seat activation improvements, giving you more control over access while streamlining the process of adding and managing team members.

New permissioning functionality

We now directly enable the ability to invite someone to your account within the new share project or video experience, making collaboration more seamless and immediate. For enterprises, this capability is especially valuable because projects often involve cross-functional teams, external partners, or global stakeholders who need quick and secure access.

Seat activation improvements

We’ve refreshed the enterprise invite modal to make it easier for admins to review suggested users and issue mass invites with confidence. For large organizations, onboarding and managing teams efficiently is critical. This upgrade streamlines the setup process, reduces administrative overhead, and ensures the right people are added quickly and securely.

Looking ahead

These July enhancements demonstrate our ongoing commitment to empowering you teams with intuitive, scalable, and high-impact video solutions. From seamless screen recording and expressive voice controls to premium visual elements and streamlined collaboration, HeyGen continues to evolve to meet the complex needs of global organizations.

Experience how these updates can transform your video production workflows, elevate content quality, and give your teams the tools to scale with confidence and control.

Enjoy learning about new product releases? Please take a moment to fill out the enterprise education survey so we can better understand your preferred learning formats.

Not a user yet? Sign up for free here.

Original source

Summary

HeyGen’s June 2025 release brings smarter, faster, and more secure video creation to enterprises with AI-powered scripting, Quick Commands, Scene Split, enhanced security, and improved team collaboration.

June was an exciting month at HeyGen, highlighted by our inaugural keynote, where we showcased the future of AI-driven video creation. Building upon this milestone, our latest product enhancements empower Enterprise teams to create impactful, high-quality videos faster, smarter, and with greater collaboration and security than ever before.

Whether your objective is to elevate internal training, streamline corporate communications, or captivate audiences with marketing content, these innovations are designed to dramatically boost productivity and ensure exceptional results every time. Here’s how these improvements translate directly into benefits for your organization:

Accelerate content creation with intelligent workflows

Our latest enhancements empower your content teams to work smarter, not harder. We've introduced tools that simplify the video production process, allowing for quicker iterations and more dynamic storytelling.

Quick commands: Instant editing at your fingertips

Imagine effortlessly enhancing your videos without interrupting your workflow. With Quick Commands, simply type '/' within your script editor to instantly unlock a suite of powerful editing and enhancement tools. From GPT script writer and Voice Director to advanced visual adjustments, your team can seamlessly execute edits, significantly reducing production cycles and unlocking features you didn’t even know you had.

This translates to significant time savings for your content creators. With Quick Commands, your teams can quickly refine scripts, add effects, and make on-the-fly adjustments, accelerating content turnaround times and boosting overall productivity. It also aids in the discovery of powerful (yet sometimes hidden) features, ensuring your teams leverage the full potential of HeyGen.

GPT script writer: AI-powered scripting and refinement

Great videos start with great scripts. Our GPT-powered script assistant provides enterprise teams with intelligent, on-demand scripting support directly in your editor. Generate polished, brand-consistent scripts quickly, refine your messaging effortlessly, and maintain the highest standards of content quality across all your communications.

For large organizations, content consistency and rapid script generation are crucial. The GPT Script Writer can help standardize messaging, generate initial drafts for various campaigns, and provide intelligent suggestions for refining existing scripts. This empowers marketing, training, and communications teams to produce high-quality, on-brand video content at an unprecedented pace, reducing reliance on external copywriting resources and ensuring consistent brand voice across all video assets.

Scene split: Granular control over pacing

Structure and pacing can make or break viewer engagement. Scene Split gives you unprecedented control to precisely segment any scene, enhancing narrative flow and ensuring your message is compelling and clear. Perfect for training videos, key announcements, or engaging storytelling, this feature enables you to deliver content exactly as intended. This is particularly valuable for complex training modules, detailed product demonstrations, or impactful corporate communications where precise timing can significantly enhance clarity and retention.

Enhanced security and streamlined user management

Managing users and ensuring compliance is paramount for enterprise organizations. Our June releases bring significant improvements to engagement tracking, user consent, and administrative oversight, giving you peace of mind and more efficient team management.

New share page: Gain deeper insights and collaboration

Understanding how your content performs is critical for your team’s success. Our revamped Share Page not only consolidates video comments for easy review but also provides essential engagement metrics like views, shares, watch time, and completion rates. Plus, viewers can instantly translate your videos into multiple languages, extending your reach and ensuring your message resonates globally.

Split out consent: Delegated avatar usage for scalability

Scale your video production securely and effortlessly across teams and trusted external partners. Our Split-out Consent feature allows enterprise customers to delegate avatar video creation rights independently from avatar management. Retain absolute control over compliance and usage, ensuring secure, efficient collaboration across your entire organization.

This is a game-changer for large-scale avatar deployments and team collaboration. For organizations with numerous spokespeople, brand ambassadors, or internal subject matter experts, this feature allows designated video producers or marketing teams to create content using pre-approved avatars without needing direct access to the original avatar creator's account.

Admin control notifications: Keeping you informed

Efficient team management requires clear oversight. We've introduced robust notification enhancements to simplify the administration of your growing teams on HeyGen:

• Admins receive notifications when new free users sign up for HeyGen within your domain.
• Free users see in-app notifications when a team plan for their domain is set up.
• Free users see their request is pending until an admin accepts it within notifications.

These consolidated notifications provide critical insights for administrators. Knowing when new free users from your domain sign up allows you to identify potential team members who could benefit from a full enterprise license, facilitating seamless onboarding and team expansion. Furthermore, the clear communication to free users about pending requests ensures transparency and reduces friction in joining your established team plan. This empowers administrators to maintain better oversight, manage licenses more effectively, and ensure that all relevant users are integrated into your HeyGen ecosystem.

Ready to unlock HeyGen's latest innovations?

These powerful enhancements reflect our unwavering commitment to providing enterprise customers with intuitive, secure, and scalable video solutions tailored specifically to complex organizational demands. From advanced editing capabilities and AI-driven scripting to robust administrative oversight, HeyGen continually evolves to support your organization's ambitious goals.

Discover firsthand how these June 2025 product updates can revolutionize your enterprise video production workflows, dramatically improve content quality, and scale confidently and securely.

Not a user yet?

Sign up for free here.

Original source

Summary

Meet the most powerful AI video creation platform ever built. You can control tone, pacing, gestures, and emotion with unmatched precision, all through an intuitive editor that puts you in charge.

In video storytelling, delivery is everything. It’s not just about

what

you say, it’s

how

you say it.

The subtlest shift in tone, the briefest pause, and the smallest gesture can transform a story from one that is merely heard into one that is deeply felt. And now, with HeyGen’s AI Studio, you’re in full creative control. It empowers you to shape your story with unmatched precision, crafting experiences that resonate deeply with your audience.

Forget the cameras, the studios, and the endless learning curves. We're putting powerful tools in your hands, giving you granular control over each moment and ensuring consistent, high-quality videos that resonate. This isn't just about making video creation easier. It's about raising the bar for what's possible, putting you squarely in the director's chair, regardless of your prior experience.

The way you create videos has transformed. Welcome to AI Studio.

Today, over 15 million people across 179 countries—including more than 100,000 paying active users—use HeyGen to share their stories and create engaging, high-quality videos.

Born from extensive user feedback, AI Studio is HeyGen's fresh, intuitive core. We've fundamentally rethought how video creation should feel—accessible, intuitive, and empowering for everyone.

Gone are the days of complex interfaces and wrestling with timelines. We've streamlined the process, creating a workspace that feels as familiar as your favorite word processor or presentation software. And it all starts with a script.

Unprecedented avatar control: Fine-tuning every detail

We believe in control over your on-screen talent (think avatars). These A-roll controls aren't just about features; they're about empowering you to cross the invisible quality threshold – that point where your audience no longer perceives the technology behind the creation and instead becomes fully immersed in your message. By giving you command over the subtle yet crucial aspects of delivery, we're helping you create authentic and impactful videos.

With Voice Director, you conduct your avatar's performance like a seasoned maestro. Emphasize a phrase with commanding power. Whisper a word, drawing your audience into a moment of intimacy. Pause for dramatic effect, letting the silence amplify your message.

Want even more control? With Voice Mirroring, your avatar can replicate your own voice, capturing the unique melody, inflection, and emotional nuance that makes your delivery distinctly yours, bridging the uncanny valley with stunning accuracy. Transcending simple text-to-speech, this technology lends an authentic and personal touch to your visual stories.

But it’s not just about the sound. You now have unprecedented control over your talent's visual presence.

Infuse life into your video avatar with natural, expressive movements using Gesture Control. For those using their own video footage, Gesture Control lets you link specific words or phrases in your script to pre-recorded gestures, enabling deliberate and impactful visual cues.

With Avatar Movement Preview, you can also see exactly how your avatar will move and interact within your scene before you finalize, eliminating guesswork and ensuring your vision is perfectly realized.

Because ‘close enough’ simply isn’t good enough when you’re striving for genuine connection. This isn't just about creating videos; it's about crafting experiences.

Inside the Build with Leo Rofe and Adam Halper

Want to see how AI Studio came together? Join product managers Leo Rofe and Adam Halper as they offer an exclusive glimpse in our "Inside the Build" series. Hear firsthand about the ideas, challenges, and key moments that shaped our latest innovations.

In the works: A look ahead at AI video innovation

The innovation doesn't stop here. Here’s a glimpse into our upcoming editing capabilities, designed to give you the same level of creative power over your supporting visuals:

• Camera Control: Imagine directing virtual camera movements within your scene, adding dynamism and visual interest without ever picking up a physical camera.
• Premium Motion Elements: Elevate your videos with professionally designed motion graphics and animations that are seamlessly integrated and customizable.
• Magic Apply B-roll: Effortlessly find and integrate relevant B-roll footage that intelligently aligns with your script and the overall tone of your video.
• Generative Elements: Explore the power of AI to generate unique visual elements on demand, tailored to your specific needs and creative vision.
• Prompt-Based Editing: Describe the visual changes you want to see, and let AI intelligently edit your B-roll, making post-production faster and more intuitive than ever before.

These upcoming features represent our ongoing commitment to pushing the boundaries of AI video generation, providing you with a comprehensive suite of tools to bring your most ambitious video ideas to life end-to-end.

We're not just offering tools; we're providing a canvas for your vision, a stage for your voice, and the power to connect with your audience on a deeper level.

HeyGen is a tool for the masses. It’s a new medium for the video itself — a dynamic, malleable material underlying video that can grow, shift, and generate whatever you want it to be.

This is your invitation to play and experiment with a new medium to free your stories.

Watch the keynote recording to see CEO Joshua Xu and team unveil a new era of AI video:

Original source