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.
Idle
$0.1per run·~10 / $1
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.
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.
| Parameter | Required | Description |
|---|---|---|
| image | Yes | Portrait image used to define the avatar's appearance. |
| audio | Yes | Audio 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. |
| prompt | No | Optional text guidance for the avatar's movement, expression, or performance style. |
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 duration | Price |
|---|---|---|
| 1 s | 4 s (minimum) | $0.40 |
| 4 s | 4 s | $0.40 |
| 5 s (anything above 4 s, up to 5 s) | 5 s | $0.50 |
| 10 s | 10 s | $1.00 |
| 30 s | 30 s | $3.00 |
| 60 s | 60 s | $6.00 |
| 120 s | 120 s | $12.00 |
| 300 s | 300 s (maximum) | $30.00 |
| 600 s (longer than 300 s) | 300 s (maximum) | $30.00 |
A run with the default settings costs $0.40.
image and audio are required.300 seconds. Nonempty recordings shorter than 4 seconds are padded with trailing silence for generation.4 seconds.300 seconds.prompt is optional.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/bytedance/omni-human-2.0 with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Omni Human 2.0 below.
set -euo pipefail
: "${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
doneconst 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));
}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 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.
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.
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.
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.
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.
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.