Adam Halper

PM avatars and voice @ Heygen

[Adam Halper @Adam_Halper]

To create this video, I just had to record myself talking for 15s in my bedroom.

Avatar V allows you create studio-quality videos of yourself without the setup or hassle.

Record 15s anywhere, customize your look, enter script, and generate!

[HeyGen @HeyGen]

We solved character consistency. Forever

Avatar V captures you in 15 seconds and holds your identity across every video.

Change the look, outfit, and setting to create unlimited versions of you.

RT + comment "AvatarV" below and I'll DM 100 credits to test it out (must follow)

[Adam Halper @Adam_Halper]

@oneeyekeh @_lovablecurves @HeyGen Thanks! Dmed

[||| @Imad_Phelps]

Getting close to cracking scene and character
consistency.

First attempt at trying to maintain both for longer than a minute: 🏔️❄️🏂

[HeyGen @HeyGen]

Avatar V API is live at $0.05/sec

The highest-quality AI avatar model for developers

Benchmarked against Veo 3.1, Kling O3 Pro, OmniHuman 1.5, and Seedance 2.0 on cross-scene talking-head generation

Avatar V won every category

Research report + API ↓

[Adam Halper @Adam_Halper]

@thekingonchain @Miguel07Code Hi @thekingonchain - we’re rolling out Avatar V custom motion feature gradually to all users. If you don’t see it yet, it should become available within the next 24 hours. Or send me a DM and will get you access right away

[ヴァン｜YouTube自動化構築 @gold_force_guri]

AIで動画作るルート確立した

①GPT Image 2 → 部屋とキャラ画像
②HeyGen Avatar V → リップシンク動画
③HyperFrames → テロップ自動付加

CapCut使うところを全部AI/コードで処理。
編集タイムライン触らずSNS投稿レベル完成。

画像作成から動画完成テロップ入りまで7分以内で完成　動画作りのコスト下がりすぎ

[||| @Imad_Phelps]

I’ve been experimenting with a way to create consistent animated scenes using HeyGen.

Same world, consistent scenes, new variations on demand.

This can power videos, products, or ambient experiences.

Here’s the workflow ↓

[Adam Halper @Adam_Halper]

@JohnWardHere @HeyGen Hi @JohnWardHere, I’m Adam, PM of Avatars at HeyGen. You can use Seedance 2 with your custom avatars through our Avatar Shots feature. DM me if you have any questions!

[Adam Halper @Adam_Halper]

@liu8in 🔥🔥

[Adam Halper @Adam_Halper]

@HeyGen Huge!

[Adam Halper @Adam_Halper]

My favorite way to create videos now

[James Russo @Rames_Jusso]

https://t.co/HH9fj9nteY

[Andrej Karpathy @karpathy]

Yes it's the tractable form of brain upload. There's a ton of scifi on brain uploads that requires way too exotic tech (scanning and simulating brains etc), when we're about to get a lossy and approximate version of that *a lot* sooner via LLM simulators. You can easily imagine a "brain upload" startup - you show up for a few days to carry out detailed video interviews, then they use all that data with an LLM finetuning process to "upload" you and give you an API endpoint of your simulation that you can talk to. Look at what's already possible with HeyGen as an example, but combine it with an LLM model that has deep knowledge and personality. Trippy and admittedly kind of dystopian but in principle quite possible around now.

[HeyGen @HeyGen]

LA community day was a good one.

People came through, created their Digital Twins for Avatar V, and learned how to prompt in Seedance 2.0 for shots they had in mind.

Everyone walked away with their avatar dialed in and ready to create.

Appreciate everyone who came through 🤝

[Adam Halper @Adam_Halper]

@awooooooowa @HeyGen Works with generated avatars too!

[Adam Halper @Adam_Halper]

@JesusPlazaX @jerrod_lew @HeyGen Yes, it supports 175+ languages!

[Joshua Xu @joshua_xu_]

Introducing Avatar V. We’ve solved character consistency. Forever.

Record yourself once for 15 seconds. From there, you can show up anywhere, in any look, and it still feels like you. Any photo becomes a video that looks, moves, and speaks like you, down to your mannerisms and quirks.

This is the most advanced AI avatar model in the world.

And we know that’s a big claim, so we brought the data to prove it.

Thread below:

[Allen Lattimer @allen_lattimer]

We weren’t missing better AI avatars—

we were missing consistent ones.

Because the moment you change the scene, everything drifts.

Face, expressions, identity—gone.

That’s what held AI video back.

This fixes it completely.

[Joshua Xu @joshua_xu_]

We put the top avatar models head to head in blind tests, and Avatar V was chosen more often than any other model, showing what “better” actually means to users.

[Rafael Estrela | IA @TextoCriativo]

O que mais impressiona aqui não é a tecnologia — é a consistência da identidade.

Pela primeira vez, o “eu digital” deixa de ser uma simulação…
e passa a ser uma extensão contínua de quem você é.

Isso muda tudo: criação, escala e até presença.

HeyGen não criou apenas um avatar.
Criou continuidade humana no mundo digital.

[Jerrod Lew @jerrod_lew]

Introducing HeyGen Avatar V.

This is the most advanced AI avatar model yet.

Avatar V focuses on character consistency, letting you move your character to new places and changing their clothes.

Here's how to get started on @HeyGen.

#Ad