HeyGen Avatar V Digital Twin is a fast AI avatar video generation model that creates natural digital twin videos from text or audio with lip-sync, optional captions, background removal, and MP4/WebM output. Ready-to-use REST inference API for digital humans, virtual presenters, product explainers, marketing videos, training content, social media clips, and professional avatar video workflows with simple integration, no coldstarts, and affordable pricing.
Idle
$0.12per run·~83 / $10
HeyGen Avatar IV Digital Twin generates a talking avatar video from a selected HeyGen digital twin avatar and an uploaded audio clip. It is designed for presenter videos, spokesperson content, personalized avatar delivery, and other avatar-driven speaking workflows with flexible output controls.
Digital twin avatar workflow Use a prebuilt digital twin avatar to generate speaking video from audio.
Audio-driven speech performance Upload an audio clip to drive the avatar’s timing, expression, and speaking delivery.
Flexible framing controls Choose aspect ratio, fit mode, and output resolution to match your target platform.
Optional background removal
Enable remove_background for supported matting-enabled avatars.
Optional caption export
Enable caption to generate a sidecar SRT subtitle file alongside the video.
Production-ready API Suitable for personalized presenter videos, internal communications, ads, explainers, and virtual spokesperson workflows.
| Parameter | Required | Description |
|---|---|---|
| avatar | Yes | Selected HeyGen digital twin avatar. |
| audio | Yes | Audio clip used to drive the avatar video. |
| fit | No | How the avatar is framed in the output, such as cover. |
| remove_background | No | Remove the avatar background. Requires a matting-enabled avatar. |
| caption | No | Generate a sidecar SRT caption file alongside the video. |
| output_format | No | Output video format. Default: mp4. |
| resolution | No | Output resolution, such as 720p. |
| aspect_ratio | No | Output aspect ratio, such as 16:9. |
fit, resolution, and aspect_ratio.remove_background or caption if needed.Generate a polished office presenter video from a digital twin avatar and a short voice clip for internal announcements or marketing content.
Pricing is based on the uploaded audio duration.
| Audio Duration | Cost |
|---|---|
| 1s | $0.12 |
| 5s | $0.60 |
| 6s | $0.72 |
| 7s | $0.84 |
| 8s | $0.96 |
| 10s | $1.20 |
| 15s | $1.80 |
caption when the final video needs accessible subtitles.remove_background if the selected avatar supports matting.aspect_ratio to your final platform, such as 16:9 for widescreen delivery.avatar and audio are required.remove_background requires a matting-enabled avatar.caption generates a sidecar SRT file, not burned-in subtitles.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/heygen/avatar-v/digital-twin with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Avatar V Digital Twin below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"avatar": "Abigail Sofa Front",
"audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
"fit": "cover",
"remove_background": false,
"output_format": "mp4",
"resolution": "720p",
"aspect_ratio": "16:9"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/heygen/avatar-v/digital-twin" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/heygen/avatar-v/digital-twin";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"avatar": "Abigail Sofa Front",
"audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
"fit": "cover",
"remove_background": false,
"output_format": "mp4",
"resolution": "720p",
"aspect_ratio": "16:9"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"avatar": "Abigail Sofa Front",
"audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
"fit": "cover",
"remove_background": False,
"output_format": "mp4",
"resolution": "720p",
"aspect_ratio": "16:9"
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/heygen/avatar-v/digital-twin", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout"}:
raise RuntimeError(result)
if status not in {"created", "processing"}:
raise RuntimeError(f"Unexpected status: {status}")
time.sleep(2)Avatar V Digital Twin is a Heygen model for talking-avatar generation, exposed as a REST API on WaveSpeedAI. HeyGen Avatar V Digital Twin is a fast AI avatar video generation model that creates natural digital twin videos from text or audio with lip-sync, optional captions, background removal, and MP4/WebM output. Ready-to-use REST inference API for digital humans, virtual presenters, product explainers, marketing videos, training content, social media clips, and professional avatar video workflows with simple integration, no coldstarts, and affordable pricing. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/heygen/heygen-avatar-v-digital-twin.
Avatar V Digital Twin starts at $0.12 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `audio`, `aspect_ratio`, `resolution`, `avatar`, `fit`, `output_format`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/heygen/heygen-avatar-v-digital-twin.
Median end-to-end generation time on WaveSpeedAI is around 185 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (Heygen). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.