HeyGen Avatar IV overview
HeyGen Avatar IV by HeyGen
HeyGen built Avatar IV to create lifelike talking videos from a single photo, with synchronized voice, facial expressions and hand gestures. The catalog lists control over gestures and expressiveness.
HeyGen Avatar IV specs
- Model ID
heygen/avatar-iv- Developer
- HeyGen
- Input
- Image, Text, Video
- Output
- Video
- Endpoint
POST https://api.aimlapi.com/v2/video/generations
Expression follows the voice
HeyGen says an audio-to-expression engine in Avatar IV generates facial movement from vocal tone, rhythm and emotion. The delivery of your audio therefore shapes how the avatar looks while speaking.
Write or record each line with the emotion and pacing you want. Then check whether the face and hands match the mood of each sentence.
Settings worth choosing first
Expressiveness sets the energy and range of facial and body movement. Render the same script on low and on high to see how much movement suits your content.
Aspect ratio accepts 16:9, 9:16, 1:1, 4:5, 5:4 or auto. Use 9:16 for vertical social video and 16:9 for training or product explanations. Auto keeps the ratio of the source and falls back to 16:9 when the source cannot be read.
Avatar IV or Avatar V
The catalog describes HeyGen Avatar V as the highest-fidelity HeyGen engine. It takes a photo avatar or a digital twin.
If expressive movement matters for your clips, render one short script on Avatar IV and on Avatar V. Compare the face and hand movement on your own avatar.
Use cases
Produce an avatar-led video ad from a written script in 9:16 or 1:1.
Narrate a training module with a consistent presenter driven by an audio track.
Explain a product feature with a talking avatar in 16:9.
Tell a short story in a social clip with expressiveness set to high.
HeyGen Avatar IV API pricing
| Usage | Price | Unit |
|---|---|---|
| Video generation | $0.038 |
Prices from the AI/ML API price list, checked on Nov 12, 2026.
How to use the HeyGen Avatar IV API
View docsBuild with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v2/video/generations' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "heygen/avatar-iv",
"avatar_id": null
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "heygen/avatar-iv",
"avatar_id": null
}
response = requests.post("https://api.aimlapi.com/v2/video/generations", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v2/video/generations", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "heygen/avatar-iv",
"avatar_id": null
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());The request returns a generation id. Poll GET https://api.aimlapi.com/v2/video/generations?generation_id=<id> until the status is completed.
HeyGen Avatar IV FAQ
How much does HeyGen Avatar IV cost?
HeyGen Avatar IV costs $0.038 on AI/ML API, billed as you go with no subscription.
What do I send to generate a video?
Send a script or an audio track together with a HeyGen photo avatar. The result is a talking-avatar video.
What does the expressiveness setting change?
It sets the energy and range of facial and body movement, with values low, medium and high. Compare the values on the same script, since the right level depends on the tone of the content.
What happens when I choose auto for the aspect ratio?
Auto keeps the aspect ratio of the source. If the source ratio cannot be read, the output is 16:9.
Which output resolutions can I request?
You can request 720p or 1080p. Use 720p to review a draft and 1080p for the version you publish.
What is the HeyGen Avatar IV model ID?
Use heygen/avatar-iv as the model parameter. Requests go to https://api.aimlapi.com/v2/video/generations with your AI/ML API key.