#2 for realistic voice · 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
Avatar 6 Turbo
Newby HeygenReleased 17 November 2026
Give it a single photo, or a short clip of a person, plus the words they should say, and it hands back a finished video of that person speaking them, lips matching the voice. You can type a script for it to read out, or supply your own voice recording. It is built for the moment a buyer sits down to do: making a person on screen say something they never filmed themselves saying. Two runs will not give the same result twice, so save the take you like, and it does not read long documents, so jobs that mean hours of footage or pages of text need a different kind of model.
Where your request runs
One company runs this model. OpenDunes sends every request to it.
In 2K: 29,12 DA a second with sound.
You pay the price of the provider that served your request. Prices read 04:33 · speed over the last 30 minutes · uptime over 3 days.
What it costs
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
Everyday jobs, priced
- When you pay
- After the answer, from your balance. Nothing is held.
- Why it varies
- The length, the sound and the resolution.
- After each one
- The exact charge shows on the request.
Call it in code
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/heygen-avatar-6-turbo",
"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.
Limits
The hard numbers — what it can take in, what it can give back, and where it stops.
- Context window
- not stated
- Max output
- not stated
- Reads at once
- not stated
- Longest reply
- not stated
- Tokenizer
- Other
- Released
- 17 Nov 2026
Questions about Avatar 6 Turbo
How much does Avatar 6 Turbo cost in dinars?
About 16,64 DA per second of video.
Is Avatar 6 Turbo free? Can I try it?
No. You pay per use from your balance in dinars, with no subscription. The chat has free models for free messages every day.
What is Avatar 6 Turbo best for?
Give it a single photo, or a short clip of a person, plus the words they should say, and it hands back a finished video of that person speaking them, lips matching the voice. You can type a script for it to read out, or supply your own voice recording. It is built for the moment a buyer sits down to do: making a person on screen say something they never filmed themselves saying. Two runs will not give the same result twice, so save the take you like, and it does not read long documents, so jobs that mean hours of footage or pages of text need a different kind of model.
Avatar 6 Turbo or Avatar 6?
Avatar 6 costs 16,64 DA more for the same second of video.
How do I pay for Avatar 6 Turbo without an international card?
Add credit in dinars with your Edahabia or CIB card. Every model, Avatar 6 Turbo included, is paid from that balance. No foreign card, no conversion.
Does Avatar 6 Turbo work in Arabic, French or Darja?
Heygen names no languages for Avatar 6 Turbo. Arabic, French and Darja: not stated.
How long can a clip be, and does it make sound?
Clip length: not stated. Sound: not stated.
Can it animate my photo, or make a vertical video?
No. Vertical 9:16: not stated.
Who makes Avatar 6 Turbo, and when was it released?
Heygen. Released 17 November 2026.
Other Heygen models, priced in dinars
See all Heygen modelsAvatar 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.
Give it a photo of a person, a short clip of them, or both, plus a voice recording, and it hands back a finished video of that person speaking, with the lips matched to the sound. It can also read a typed script, so a buyer can sit down and make a talking video without ever filming the person saying the words. It writes video, not text, and it is billed by the second of footage it produces. Two runs will not give the same take twice, so keep the one you like, and it does not read long documents, so jobs that mean hours of film or pages of writing need a different kind of model.
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.
