Avatar video
Avatar video
HeyGen Avatar IV
A library avatar or your own photo reads your script or audio, with natural lip sync.
You need: a script or audio
GlobalGPT×
HeyGen· Official partnerAll HeyGen models on GlobalGPT
HeyGen models for avatar video, generated video, images, voice and translation. All with one GlobalGPT account.
What are you starting with?
Video
Video
HeyGen Video 1New
Text or a first frame to a 5–30 second clip, up to 2K. Up to 9 references keep people consistent.
You need: a prompt, optional images
Image
Image
HeyGen Image 1New
Put the person from 1–5 photos into a scene photo, with the same face every time.
You need: face photos + a scene
Voice
Voice
HeyGen Voice 1New
Expressive text to speech for ads, intros and narration.
You need: up to 10,000 characters
Voice
Voice
HeyGen Voice 1 TurboNew
The same voices, faster, built for long scripts.
You need: up to 10,000 characters
TranslationEnglish → Español
Translation
HeyGen Video Translate
Translate the speech in a video and re-sync the lips. Speed or Precision mode.
You need: a video with speech
Use them together
One photo can become a presenter video in many languages.
Questions
Are these the official HeyGen models?
Yes. GlobalGPT is an official HeyGen partner, and these are the same models HeyGen offers, available right inside GlobalGPT.
Where do my results go?
Every video, image and audio file is saved in Assets, next to the rest of your work.
Which model should I use for a talking presenter?
Avatar IV. Use Video 1 when you want a generated scene rather than a person reading a script.
What's the difference between Voice 1 and Voice 1 Turbo?
They share the same voices. Voice 1 is more expressive; Turbo is faster and suits long scripts.
Start creating with HeyGen
Pick a model above, or open GlobalGPT and choose HeyGen in any video, image or audio tool.
Open GlobalGPT