HeyGen Avatar IV
Turn one portrait and a script into a speaking 720p video. The script and voice determine the output length.
| Model ID | Alias | Endpoint |
|---|---|---|
heygen/avatar-iv |
heygen-avatar-iv |
Video generation |
Input modes
| Mode | References | Reference roles |
|---|---|---|
reference Reference media |
1 | reference_image |
Parameters
| Parameter | Description | Values | Default | Required |
|---|---|---|---|---|
resolution |
Resolution: Output resolution. | 720p |
720p |
No |
aspect_ratio |
Aspect ratio: Output aspect ratio. | 16:9, 9:16, 4:5, 5:4, 1:1, auto |
16:9 |
No |
n |
Outputs per request: Number of outputs from one API request (one Job), not the application batch size. For multiple Jobs, submit separate requests; n=1 does not prevent application-managed batching. | 1 |
1 |
No |
Examples
reference input:
{
"model": "heygen/avatar-iv",
"input": {
"type": "reference",
"prompt": "Welcome to the team. Here is what to expect on your first day.",
"references": [
{
"role": "reference_image",
"file_id": "file_..."
}
]
},
"parameters": {
"resolution": "720p",
"aspect_ratio": "16:9",
"n": 1
}
}
The authoritative contract is GET /v1/models/heygen/avatar-iv?view=contract. A valid parameter does not mean every channel can run it, so quote the complete request. Prices and channels are listed in Model Market.
Send one portrait as reference_image and the exact script as input.prompt. The fal route produces a speaking 720p MP4 using the fixed Warm Pro Narrator voice.
The script and synthesized speech determine the runtime. Leave out duration and generate_audio. fal lists $0.10 per output second. The task total is unknown before rendering, and final settlement uses the matching fal Billing Events charge. Requests with max_cost require a task estimate and are unavailable on this route.