OmniHuman 2.0 Talking Avatar Video API

bytedance/omni-human-2.0

OmniHuman 2.0 Talking Avatar turns a portrait image and audio recording into a lifelike talking-avatar video, making it suitable for digital humans, virtual presenters, dubbing, social 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

Idle

$0.1per run·~10 / $1

ExamplesView all

Related Models

README

OmniHuman 2.0

OmniHuman 2.0 creates a talking-avatar video from a portrait image and an audio recording. The image defines the character's appearance, while the supplied audio drives the speaking performance and timing.

Use an optional prompt to guide the avatar's movement, expression, or overall performance style. It is designed for virtual presenters, digital humans, explainers, social content, and other speech-driven avatar workflows.

Why Choose This?

  • Image-and-audio avatar generation
    Turn a portrait image and speech recording into a talking-avatar video.

  • Audio-driven performance
    Use the supplied audio to drive the avatar's speaking performance and timing.

  • Prompt-guided motion
    Add optional instructions for expression, movement, or performance style.

  • Long-form avatar video
    Process up to the first 300 seconds of an audio recording; longer recordings are trimmed automatically.

  • Simple workflow
    Provide an image and audio recording, then generate the completed avatar video.

Parameters

ParameterRequiredDescription
imageYesPortrait image used to define the avatar's appearance.
audioYesAudio recording used to drive the avatar. Any nonempty recording is accepted. Only the first 300 seconds are processed; shorter-than-4-second recordings are padded with trailing silence for generation.
promptNoOptional text guidance for the avatar's movement, expression, or performance style.

How to Use

  1. Upload a portrait — Provide a clear image with the subject's face visible. Images are converted to JPEG and fitted to the supported dimensions; extreme aspect ratios are center-cropped.
  2. Upload speech audio — Supply the recording that should drive the avatar performance.
  3. Add a prompt optional — Describe the desired movement, expression, or performance style.
  4. Submit — Generate and retrieve the talking-avatar video.

Pricing

Pricing is based on the length of the audio recording, capped at 300 seconds; padding does not add charges beyond the 4-second minimum.

Each billed second of audio is charged at the same rate. Audio duration is rounded up to the next whole second, with a minimum billed duration of 4 seconds and a maximum of 300 seconds. Every second beyond the first 4 adds $0.10 (audio of 6 s versus 5 s).

Audio length (audio)Billed durationPrice
1 s4 s (minimum)$0.40
4 s4 s$0.40
5 s (anything above 4 s, up to 5 s)5 s$0.50
10 s10 s$1.00
30 s30 s$3.00
60 s60 s$6.00
120 s120 s$12.00
300 s300 s (maximum)$30.00
600 s (longer than 300 s)300 s (maximum)$30.00

A run with the default settings costs $0.40.

Best Use Cases

  • Virtual presenters — Create presenter-style videos from portrait images and recorded speech.
  • Digital humans — Animate portrait characters for speech-driven content.
  • Product explainers — Turn narration into avatar-led product presentations.
  • Educational content — Create instructor or presenter videos for courses and training.
  • Social media content — Generate talking-character clips from existing portraits.
  • Localized content — Reuse the same portrait with different audio recordings for multiple versions.

Pro Tips

  • Use a clear, well-lit portrait with the face clearly visible.
  • Use clean speech audio with minimal background noise.
  • Keep the prompt focused on natural expressions and movement.
  • Avoid overly complex or conflicting motion instructions.
  • Use shorter audio samples when testing a new portrait or prompt before generating longer videos.

Notes

  • image and audio are required.
  • Long recordings are automatically trimmed to their first 300 seconds. Nonempty recordings shorter than 4 seconds are padded with trailing silence for generation.
  • Billing duration is rounded up to the next whole second.
  • The minimum billed duration is 4 seconds.
  • The maximum billed duration is 300 seconds.
  • prompt is optional.

Related Models

  • Seedance 2.5 Talking Avatar — Create talking-avatar videos from a portrait image and speech audio.
  • InfiniteTalk — Generate speech-driven talking-character videos from image and audio inputs.
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.

Omni Human 2.0 API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/bytedance/omni-human-2.0 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 Omni Human 2.0 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"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/bytedance/omni-human-2.0" \
  -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/bytedance/omni-human-2.0";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${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"
}

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/bytedance/omni-human-2.0", 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)

Omni Human 2.0 API — Frequently asked questions

What is the Omni Human 2.0 API?

Omni Human 2.0 is a ByteDance model for talking-avatar generation, exposed as a REST API on WaveSpeedAI. OmniHuman 2.0 Talking Avatar turns a portrait image and audio recording into a lifelike talking-avatar video, making it suitable for digital humans, virtual presenters, dubbing, social 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 Omni Human 2.0 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/bytedance/omni-human-2.0.

How much does Omni Human 2.0 cost per run or per second?

Omni Human 2.0 starts at $0.1 per run or per second. 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 Omni Human 2.0 accept?

Key inputs: `prompt`, `image`, `audio`. 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/bytedance/omni-human-2.0.

How long does Omni Human 2.0 take to generate?

Reported generation time on WaveSpeedAI is around 133 seconds per request. This is an estimate, not a latency guarantee; queue time and input settings can change the total wait. live status is visible in the prediction record.

Can I use Omni Human 2.0 outputs commercially?

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

llms.txt — bytedance/omni-human-2.0 for AI agents and LLMs