Nano Banana 2.1 is LIVE — Google's Latest | Try Now →

heygen/avatar-iv

HeyGen Avatar IV turns portrait images and speech recordings into expressive talking-avatar videos with expression control, optional backgrounds, and up to 1080P output for digital humans, virtual presenters, personalized content, and avatar video workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Talking Avatar
Input

Drag & drop or click to upload

preview

Drag & drop or click to upload

Loading…

Drag & drop or click to upload

Idle

$0.1per run·~10 / $1

ExamplesView all

Related Models

README

HeyGen Avatar IV

HeyGen Avatar IV turns a portrait image and speech audio into a talking-avatar video. Add optional performance directions, adjust expressiveness, and choose the resolution and background that fit your content.

Why Choose This?

  • Photo-to-avatar video — Bring a portrait to life with your own speech audio.
  • Performance direction — Guide expressions and movement with an optional prompt.
  • Expression control — Choose low, medium, or high expressiveness.
  • Flexible presentation — Select resolutions up to 1080p and optionally add a background image.
  • Multiple aspect ratios — Create landscape, portrait, square, and other supported layouts.

Parameters

ParameterRequiredDescription
imageYesPortrait image URL or upload.
audioYesSpeech audio URL or upload used to drive the avatar.
backgroundNoOptional background image URL or upload.
promptNoOptional directions for expressions and movement. Maximum 5,000 characters.
resolutionNo360p, 480p, 540p, 720p, or 1080p. Default: 1080p.
aspect_ratioNo16:9, 9:16, 1:1, 5:4, or 4:5. Leave empty to use the closest supported ratio to the input image.
expressivenessNolow, medium, or high. Default: low.

How to Use

  1. Upload a portrait — Provide a clear image of the person.
  2. Add speech audio — Upload the recording the avatar should speak.
  3. Adjust presentation optional — Set performance guidance, expressiveness, background, resolution, or aspect ratio.
  4. Submit — Generate and retrieve the talking-avatar video.

Pricing

Pricing is based on the input audio duration at $0.10 per billed second.

Audio duration is rounded up to the next whole second, with billing capped at 600 seconds per request.

Audio LengthBilled DurationPrice
10s10s$1.00
10.2s11s$1.10
60s60s$6.00
600s600s$60.00

The same rate applies across all supported resolutions and aspect ratios.

Best Use Cases

  • Presenter videos — Create spoken introductions, announcements, and presentations.
  • Learning content — Turn recorded explanations into avatar-led educational videos.
  • Personalized messages — Pair a portrait with custom speech audio.
  • Marketing content — Create talking-presenter videos for campaigns and promotions.
  • Social content — Produce speech-driven avatar videos for short-form content.

Pro Tips

  • Use a sharp portrait with a clearly visible face.
  • Use clean speech audio with minimal background noise.
  • Keep performance directions clear and specific.
  • Choose expressiveness based on the tone of the speech.
  • Use a background image when you need more control over the final presentation.

Notes

  • image and audio are required.
  • resolution defaults to 1080p.
  • expressiveness defaults to low.
  • Leave aspect_ratio empty to use the closest supported ratio to the portrait.
  • The original image dimensions are not preserved automatically.
  • Text scripts and avatar IDs cannot replace the required image and audio inputs.
  • Billing is based on audio duration, not resolution.

Related Models

  • HeyGen Avatar IV — Create talking-avatar videos from a portrait image and speech audio.
  • HeyGen Avatar V — Create avatar videos with the newer HeyGen Avatar generation.
Note:This website uses AI models provided by third parties. Documentation prices are for reference and may be outdated. The Generate button shows an estimate; the final task charge prevails.

Avatar Iv API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/heygen/avatar-iv 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 Iv below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "expressiveness": "low"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/heygen/avatar-iv" \
  -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="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"

# 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' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/heygen/avatar-iv";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
        "resolution": "1080p",
        "aspect_ratio": "16:9",
        "expressiveness": "low"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${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", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
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 = {
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "expressiveness": "low"
}

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-iv", 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 = 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", "deleted"}:
        raise RuntimeError(result)
    time.sleep(2)

Avatar Iv API — Frequently asked questions

What is the Avatar Iv API?

Avatar Iv is a Heygen model for talking-avatar generation, exposed as a REST API on WaveSpeedAI. HeyGen Avatar IV turns portrait images and speech recordings into expressive talking-avatar videos with expression control, optional backgrounds, and up to 1080P output for digital humans, virtual presenters, personalized content, and avatar video workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Avatar Iv API?

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 Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/heygen/heygen-avatar-iv.

How much does Avatar Iv cost per run?

Avatar Iv starts at $0.1 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.

What inputs does Avatar Iv accept?

Key inputs: `prompt`, `image`, `audio`, `aspect_ratio`, `resolution`, `background`. 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-iv.

How do I get started with the Avatar Iv API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Avatar Iv outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Heygen). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.

llms.txt — heygen/avatar-iv for AI agents and LLMs