Pixazo API→Models→OmniHuman
Pixazo API→Models→OmniHuman

OmniHuman 1.5 API - AI Lipsync & Video Generation APIs

by BytePlus

View as Markdown

OmniHuman 1.5 API, developers can synchronize any audio with video to produce natural lip movements, facial expressions, and head motion. The API excels at multilingual dubbing, avatar animation, and creating talking head videos for education, marketing, and entertainment. OmniHuman's sophisticated algorithms ensure natural-looking results that maintain the character and emotion of the original content.

Get API Key
OmniHuman API

Models Version

LIMITED TIME OFFER

Get $5 Free Credit on First Payment

No strings attached — add funds and get $5 bonus instantly

Claim Your $5 →

OmniHuman v1.5 Audio to Video (Ref Image + Ref Audio to Video — Lipsync) API Documentation

https://gateway.pixazo.ai/bytedance-omnihuman-v1-5-290/v1

Authentication

All requests require an API key passed via header.

HeaderTypeRequiredDescription
Ocp-Apim-Subscription-KeystringYesYour API subscription key

ByteDance Omnihuman v1.5 generate request - ByteDance Omnihuman v1.5

Request Code

POST https://gateway.pixazo.ai/bytedance-omnihuman-v1-5-290/v1/bytedance-omnihuman-v1-5-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "image_url": "https://storage.googleapis.com/falserverless/example_inputs/omnihuman_v15_input_image.png",
  "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/omnihuman_v15_input_audio.mp3",
  "resolution": "1080p"
}
import requests

url = "https://gateway.pixazo.ai/bytedance-omnihuman-v1-5-290/v1/bytedance-omnihuman-v1-5-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "image_url": "https://storage.googleapis.com/falserverless/example_inputs/omnihuman_v15_input_image.png",
    "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/omnihuman_v15_input_audio.mp3",
    "resolution": "1080p"
}

response = requests.post(url, json=data, headers=headers)
print(response.json())
const url = 'https://gateway.pixazo.ai/bytedance-omnihuman-v1-5-290/v1/bytedance-omnihuman-v1-5-request';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};
const body = {
  image_url: 'https://storage.googleapis.com/falserverless/example_inputs/omnihuman_v15_input_image.png',
  audio_url: 'https://storage.googleapis.com/falserverless/example_inputs/omnihuman_v15_input_audio.mp3',
  resolution: '1080p'
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(body)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));
curl -X POST "https://gateway.pixazo.ai/bytedance-omnihuman-v1-5-290/v1/bytedance-omnihuman-v1-5-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "image_url": "https://storage.googleapis.com/falserverless/example_inputs/omnihuman_v15_input_image.png",
    "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/omnihuman_v15_input_audio.mp3",
    "resolution": "1080p"
  }'

Output

{
  "request_id": "bytedance-omnihuman-v1-5-290_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/bytedance-omnihuman-v1-5-290_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your generate request to receive a POST callback instead of polling.

X-Webhook-URL: https://your-server.com/webhook/callback

Request Parameters - ByteDance Omnihuman v1.5 generate request

Parameter Required Type Description
image_urlYesstringPublicly accessible URL to a static image of a human face or full-body portrait. The image should clearly show the subject’s face for accurate animation.
audio_urlYesstringPublicly accessible URL to an audio file (MP3 or WAV) containing the speech to be synchronized with the subject’s lip movements.
resolutionNostringOutput video resolution. Supports "720p", "1080p", and "480p". Higher resolutions result in larger file sizes and longer processing times.

Example Request

{
  "image_url": "https://storage.googleapis.com/falserverless/example_inputs/omnihuman_v15_input_image.png",
  "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/omnihuman_v15_input_audio.mp3",
  "resolution": "1080p"
}

Response

{
  "request_id": "bytedance-omnihuman-v1-5-290_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/bytedance-omnihuman-v1-5-290_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header Value
Content-Typeapplication/json
Cache-Controlno-cache
Ocp-Apim-Subscription-KeyYOUR_SUBSCRIPTION_KEY

Response Handling

Common status codes.

CodeMeaning
202Accepted — Request queued
Bad Request
401Unauthorized
402Insufficient Balance
403Forbidden
Too Many Requests
500Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}
// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'bytedance-omnihuman-v1-5-290' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "bytedance-omnihuman-v1-5-290_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "bytedance-omnihuman-v1-5-290",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/bytedance-omnihuman-v1-5-290_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "bytedance-omnihuman-v1-5-290_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "bytedance-omnihuman-v1-5-290",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/bytedance-omnihuman-v1-5-290_019dxxxx-xxxx/output.ext"
    ],
    "media_type": "application/octet-stream"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

FieldTypeDescription
request_idstringUnique request identifier
statusstringQUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_idstringModel that processed the request
errorstring|nullError message if failed
output.media_urlarrayURLs to generated media (R2 CDN)
output.media_typestringMIME type of the output
created_atstringWhen request was created
completed_atstring|nullWhen request completed
polling_urlstringStatus URL (initial response only)

Status Values

StatusDescription
QUEUEDRequest accepted, waiting to be processed
PROCESSINGBeing processed by the model
COMPLETEDDone — output contains the result
FAILEDFailed — check error field
ERRORSystem error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

  1. Send a generate request to the API endpoint
  2. Save the request_id from the response
  3. Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
  4. When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

OmniHuman v1.5 Audio to Video (Ref Image + Ref Audio to Video — Lipsync) API Pricing

ResolutionPrice (USD)
Per second of output video$0.16