by HeygenReleased 24 August 2026
Avatar IV turns one photo of a person into a talking-head video that speaks a script you type or a recording you upload. The lips match the speech, and head movement, facial expressions and gestures follow the tone and rhythm of the voice. You get HD or Full HD video in widescreen, vertical or square, with options for captions and a new background.
You pay for what each request uses. No subscription, no minimum.
One second of video, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Second of video | 16,64 DA |
per second of video returned
One company runs this model. OpenDunes sends every request to it.
| Provider | Per second, silent | Latency | Uptime |
|---|---|---|---|
| HeyGen | 16,64 DA | … | … |
In 1080p: 16,64 DA a second with sound.
You pay the price of the provider that served your request. Prices read 15:19 · speed over the last 30 minutes · uptime over 3 days.
Send the job, then ask for it until it is ready.
import os, time, requests
BASE = "https://opendunes.com/v1"
KEY = os.environ["OPENDUNES_API_KEY"]
H = {"Authorization": f"Bearer {KEY}"}
job = requests.post(f"{BASE}/videos", headers=H, json={
"model": "heygen/avatar-iv",
"prompt": "Sunrise over the dunes of Taghit, slow pan",
"duration": 8, "resolution": "1080p",
"generate_audio": False,
}).json()
while job["status"] not in ("completed", "failed"):
time.sleep(10)
job = requests.get(job["polling_url"], headers=H).json()
print(f"{BASE}/videos/{job['id']}/content")Runs this request once on your balance.
About 16,64 DA per second of video.
No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.
Avatar IV turns one photo of a person into a talking-head video that speaks a script you type or a recording you upload. The lips match the speech, and head movement, facial expressions and gestures follow the tone and rhythm of the voice. You get HD or Full HD video in widescreen, vertical or square, with options for captions and a new background.
Deposit dinars with your Edahabia or CIB card. Every model, Avatar IV included, is paid from that balance. No foreign card, no conversion.
Heygen names no languages for Avatar IV. Arabic, French and Darja: not stated.
Clip length: not stated. Sound: not stated.
No. Vertical 9:16: yes.
Heygen. Released 24 August 2026.
HeyGen Voice Turbo speaks written text through the same ten built-in voices as HeyGen Voice at lower latency, so the audio starts sooner, across 39 languages and up to 5,000 characters a request
HeyGen Video makes a 5 to 15 second clip from a written description, a starting picture, or reference pictures, video and audio that you point it to. The clip comes back anywhere from low resolution up to 2K, in shapes from ultra-wide to vertical. It suits brand clips, product walk-throughs, equipment demos and training material with plenty of motion.
HeyGen Voice turns text into speech, 5,000 characters at a time, and sends the audio back as it is made. It speaks 39 languages with 10 default voices, and if you connect your own HeyGen account, voice clones from it work too. Pick it for voiceovers and narration across many languages.
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 7 Nov 2026.
Vertical 9:16
Same result twice No.
The same seed gives the same result.
Turn a staff photo into a spoken welcome video
Lip-sync a photo to a recorded voice message
Audio
Make a product explainer presented by an avatar