HeyGen Avatar V
Text & image to video
HeyGen's digital-twin model: built from a short video of a real person, it keeps their identity across scenes, with phoneme-level lip sync in many languages.
AI video model · By HeyGen
HeyGen Avatar III, IV and V in your Qten account: talking presenters from a photo or a short video, speaking your script.
Free plan · No credit card · Updated 2026-11-18
HeyGen Avatar
By HeyGen
3 versions of HeyGen Avatar in one Qten account, from fast drafts to the newest release.
HeyGen Avatar is HeyGen's family of talking-avatar models. Avatar IV turns a single photo plus a script or audio into a speaking video with lip sync, head movement, expressions and gestures. Avatar V builds a digital twin from a short video of a real person and keeps the identity consistent. Qten offers Avatar III, IV and V.
HeyGen is an AI video company known for avatar presenters. Its avatar models have moved from fast lip sync to full performances: Avatar III focuses on quick lip sync, Avatar IV animates any photo, including cartoons, animals and 2D or 3D characters, with natural head and hand movement, and Avatar V conditions on a short video clip of a real person to create a digital twin with phoneme-accurate lip sync across languages.
| Made by | HeyGen |
|---|---|
| Newest on Qten | HeyGen Avatar V |
| Versions on Qten | 3 |
| Native audio | Yes |
| Inputs | Text prompt · Start image · Audio |
Limits are the maker's published figures, checked 2026-11-18. What you can use may depend on your plan.
3 versions of HeyGen Avatar in one Qten account, from fast drafts to the newest release.
Text & image to video
HeyGen's digital-twin model: built from a short video of a real person, it keeps their identity across scenes, with phoneme-level lip sync in many languages.
Text & image to video
Animates a single photo with a script or audio: lip sync, head movement, micro-expressions and hand gestures. Also works for cartoons, animals and 3D characters.
Text & image to video
The earlier, faster model focused on lip sync, without advanced body motion.
| Version | What it makes | Tier | Released |
|---|---|---|---|
| HeyGen Avatar III | Text & image to video | Standard | — |
| HeyGen Avatar IV | Text & image to video | Standard | — |
| HeyGen Avatar V | Text & image to video | Standard | — |
Avatar IV brings a single photo to life with your script.
Avatar V recreates a real person from a short video.
Mouth movement that matches the words, in many languages.
Head, face and hand movement that fit the delivery.
Script: "Hi, I'm Sam from the support team. In the next minute I'll show you how to reset your password in three steps." Friendly, upbeat delivery.Script: "Welcome back to the channel! Today we're testing five budget cameras so you don't have to." Energetic YouTube host tone.Script: "Thank you for joining our onboarding. Let's start with your first project." Calm, professional tone for a training video.A consistent presenter without filming yourself.
Clear talking-head lessons at scale.
Short walkthroughs with a friendly host.
The same presenter speaking many languages.
The other video models in the same Qten account. Pick per scene, or let Qten choose.
| HeyGen Avatar | Veo | Wan | Grok Imagine | Kling | |
|---|---|---|---|---|---|
| Made by | HeyGen | Google DeepMind | Alibaba | xAI | Kuaishou |
| Newest on Qten | HeyGen Avatar V | Veo 3.1 | Wan 3 | Grok Imagine Video 1.5 | Kling 4 |
| Versions on Qten | 3 | 2 | 10 | 3 | 6 |
| Max resolution | — | Up to 1080p | Up to 1080p | Up to 1080p | Up to 1080p |
| Max length | — | Up to 8 s | Up to 30 s (Wan 3) | Up to 15 s (Video 1.5) | Up to 30 s (Kling 4) |
| Native audio | Yes | Yes | Yes (Wan 2.5+) | Yes | Yes |
| Inputs | Text prompt · Start image · Audio | Text prompt · Start image · First & last frame · Reference images | Text prompt · Start image · Reference images · Audio | Text prompt · Start image · First & last frame · Reference images | Text prompt · Start image · First & last frame · Reference images |
Limits are the maker's published figures, checked 2026-11-18. What you can use may depend on your plan.
Sign up on the Free plan. No credit card, and you get credits to start.
Write your prompt or script, then choose HeyGen Avatar as the model, or let Qten pick the best model for each step.
Review the result, edit it in Qten, and post or schedule it to YouTube, TikTok, Instagram and more.
FAQ
HeyGen Avatar is HeyGen's family of AI models that turn a photo or a short video of a person into a talking-presenter video that speaks your script.
Qten offers HeyGen Avatar III, Avatar IV and Avatar V.
Qten has a Free plan with 100 free credits and no credit card. Generating with HeyGen Avatar uses credits, depending on the version and video length. See the Pricing page for details.
Avatar IV animates a single photo, including cartoons and non-human characters. Avatar V builds a digital twin from a short video of a real person and keeps the identity consistent across scenes.
Yes. HeyGen Avatar IV turns one photo plus a script or audio into a talking video with lip sync and gestures.
No. You use HeyGen's avatar models from your Qten account with Qten credits, without a separate HeyGen plan.
Model names and logos are trademarks of their owners. Qten is not affiliated with or endorsed by them.
HeyGen Avatar and 130+ other AI models in one account. Start free.
Start creating free