curl --request POST \
--url https://api.poyo.ai/api/generate/submit \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "kling-avatar-2.0/standard",
"callback_url": "https://your-domain.com/callback",
"input": {
"image_urls": [
"https://example.com/avatar.png"
],
"audio_url": "https://example.com/voice.mp3",
"prompt": "A natural talking avatar facing the camera."
}
}
'
{
"code": 200,
"data": {
"task_id": "task-unified-1757165031-uyujaw3d",
"status": "not_started",
"created_time": "2025-11-12T10:30:00"
}
}{
"code": 400,
"error": {
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}{
"code": 400,
"error": {
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}Kling
Kling Avatar 2.0
Audio-driven avatar video generation with Kling Avatar 2.0 Standard and Pro
POST
/
api
/
generate
/
submit
curl --request POST \
--url https://api.poyo.ai/api/generate/submit \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "kling-avatar-2.0/standard",
"callback_url": "https://your-domain.com/callback",
"input": {
"image_urls": [
"https://example.com/avatar.png"
],
"audio_url": "https://example.com/voice.mp3",
"prompt": "A natural talking avatar facing the camera."
}
}
'
{
"code": 200,
"data": {
"task_id": "task-unified-1757165031-uyujaw3d",
"status": "not_started",
"created_time": "2025-11-12T10:30:00"
}
}{
"code": 400,
"error": {
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}{
"code": 400,
"error": {
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}- After submission, a
task_idwill be returned. If you provided acallback_url, when the task status becomesfinishedorfailed, a POST request will be sent to thecallback_url. - Regardless of whether
callback_urlis provided, you can retrieve the result through the unified Query Task Status endpoint.
Kling Avatar 2.0
kling-avatar-2.0/standard and kling-avatar-2.0/pro create an audio-driven avatar video from one reference image and one driving audio file.
Available Models
- kling-avatar-2.0/standard - Standard avatar video generation
- kling-avatar-2.0/pro - Pro avatar video generation with higher quality
Required Parameters
- image_urls: Reference image array. Exactly
1image is supported, andimage_urls[0]is used as the avatar image - audio_url: Driving audio URL. Audio duration must be between
2and60seconds
Optional Parameters
- prompt: Optional text prompt for the avatar video
Credit Billing
Billing is calculated from the detected audio duration, rounded up to the nearest second. Credit usage depends on the selected model and detected audio duration.Notes
- Use
image_urls, consistent with other video generation APIs. The service mapsimage_urls[0]to the upstreamimage_urlfield. audio_urlmust be an HTTP or HTTPS URL. If the file size can be detected before submission, it must be5MBor less.- This page only describes the unified submit request. Query status through the standard task status API.
Authorizations
All API endpoints require Bearer Token authentication.
Get your API Key from the API Key Management Page.
Add it to the request header:
Authorization: Bearer YOUR_API_KEY
Body
application/json