No subscription

Your presenter, reading your script

Upload one photo of the presenter, paste the script and pick a voice: HeyGen Avatar IV makes them say it, lip-synced, for as long as the script runs, and you pay for the seconds of speech. The same voice name sounds the same in every clip, so a series of training, product or welcome videos keeps one presenter and one voice. For a presenter inside a moving scene, Kling 3.0 and Veo 3.1 animate the photo from a prompt.

Try it with an example See what a clip costs

$0.50 of free credit when you verify your email. Clips from $0.38, top-ups from $5, and top-up credit never expires.

Diese Seite auf Deutsch

An example

One photo and one script, and the clip it made

An AI-made portrait of a woman holding a small amber bottle of facial serum — The photo that went in

“Hi, I'm here to show you the Luma facial serum. Three drops in the morning, three at night.”

The script, said word for word

The clip that came back

Made with HeyGen Avatar IV on November 10, 2026, from this one AI-made portrait, this script and the voice Cassidy: a 4.6-second clip, ready in about a minute and charged for its 4.6 seconds. The person does not exist, and Luma is a made-up brand.

What a clip costs

Which model to use

Today’s price for a typical clip on each model, from GenMagic’s live price list. You pay only for the clips you make.

Model	Why for this	A clip	Longest take	Up to
Avatar IVHeyGen without a subscription	a script of any length read word for word, in a voice you pick by name	$0.385 s of speech in 720p	The script's length	1080p
Kling Video v3.0 ProKling 3.0 without a subscription	a presenter in a scene, with a steady camera and clear dialogue	$1.265 s in 1080p	15 s	1080p
Veo 3.1 FastVeo 3.1 without a subscription	a quick spoken line in a scene with sound, in under a minute	$0.604 s in 720p	8 s	4K

Start from an example

Prompts that work

Each opens the studio with the prompt and the model ready. Change it, see the price, generate.

A training video intro

Welcome to the first lesson. In the next ten minutes you will learn how our booking system works, from the first call to the confirmed appointment. Keep this video open beside the system and pause whenever you like.

Avatar IV, $0.38 a clipOpen in the studio

A product walkthrough

This is the new dashboard. On the left you see today's orders, on the right the ones that still need an answer. Click any order to open it, and everything about it is on one screen.

Avatar IV, $0.38 a clipOpen in the studio

A presenter in a scene

Animate this photo: the presenter stands in a bright office, looks into the camera and says, "Here is what changed this month, in under a minute." Calm, confident voice, a small hand gesture, the camera steady at chest height, 8 seconds. Keep the face exactly as in the photo.

Kling Video v3.0 Pro, $1.26 a clipOpen in the studio

What makes the difference

How to get good results

Use a sharp, front-facing photo with the mouth visible and even light; a plain background keeps the attention on the presenter.
On Avatar IV the prompt is the script: write only what the presenter says, and split a long script into chapters so each clip is one topic.
Pick the voice by name and keep it for the whole series: Kore and Orus speak any language, the others one each (Cassidy and Andrew English, Leonie and Otto German).
Only use a photo of yourself or of someone who agreed to it, and keep an AI presenter a presenter: never script one as a customer who used the product.

Go deeper: Make a photo talk, Spoken video ads from a product photo, Explainer videos, HeyGen without a subscription, A Synthesia alternative without a plan.

Questions

How do I make an AI avatar video from a photo?

Open the studio on HeyGen Avatar IV, attach the presenter's photo, paste the script and pick a voice. The clip is the presenter reading your script, lip-synced, as long as it runs.

Do I need a HeyGen plan?

No. Avatar IV runs here per second of speech from a balance you top up; there is no avatar plan or monthly fee, and top-up credit never expires.

Which languages can the avatar speak?

English, German, Spanish, French and Japanese, each with a female and a male voice, and two multilingual voices, Kore and Orus, for any other language.

How long can an avatar video be?

As long as the script: the clip lasts as long as the words take to say, and the studio shows its price before you generate. For long scripts, one clip per chapter is easier to edit.

What does a clip cost?

Today a typical clip costs $0.38 on Avatar IV (5 s of speech in 720p), $1.26 on Kling Video v3.0 Pro (5 s in 1080p), $0.60 on Veo 3.1 Fast (4 s in 720p). The studio shows the exact price for your settings before you generate, and a clip that fails is not charged.

Make your first clip on Avatar IV

$0.50 of free credit to start. No subscription, no card to try.

Open the studio