The astronomer speaks calmly and thoughtfully in English, gently opens one hand toward the sky once, then rests it. Subtle wonder in her eyes and a small closing smile. Accurate lip sync, stable face and natural fingers. Preserve twilight lighting, locked camera, no cuts.
Kling Avatar 2.0 Pro API
kwaivgi/kling-video/ai-avatar/v2/proKling Avatar 2.0 Pro turns a character portrait and driving audio into high-fidelity talking-avatar video, with expressive gestures, object-interaction cues, and lifelike micro-movements. It preserves facial identity across longer speaking takes while refining eye motion, neck dynamics, and broadcast-ready presentation quality.
Input
Drag and drop files, paste from clipboard, or provide a URL.
1/1 files added
Drag and drop files, paste from clipboard, or provide a URL.
1/1 files added
272 / 2500
Output
ReadyEstimated: 6s × 14 = 84 credits ($0.420)
Examples
REST API
Quick Start
Authenticate, submit a valid input object, then use task_id to retrieve the video.
01
Connect to the Vidgo API
Create an API key, keep it only on your server, and send Authorization: Bearer VIDGO_API_KEY.
- Endpoint
- POST
https://api.vidgo.ai/api/generate/submit - Authentication
- Authorization: Bearer VIDGO_API_KEY
02
Submit one generation task
Replace the example URLs with publicly accessible media, then submit using model kwaivgi/kling-video/ai-avatar/v2/pro.
Submit request
REQUEST_BODY=$(cat <<'JSON'
{
"model": "kwaivgi/kling-video/ai-avatar/v2/pro",
"input": {
"image_urls": [
"https://cdn.vidgo.ai/apis/models/kwaivgi/kling-video/ai-avatar/v2/pro/v1/03/input.png"
],
"audio_url": "https://cdn.vidgo.ai/apis/models/kwaivgi/kling-video/ai-avatar/v2/pro/v1/03/audio.mp3",
"prompt": "The astronomer speaks calmly and thoughtfully in English, gently opens one hand toward the sky once, then rests it. Subtle wonder in her eyes and a small closing smile. Accurate lip sync, stable face and natural fingers. Preserve twilight lighting, locked camera, no cuts."
}
}
JSON
)
RESPONSE=$(curl --silent --show-error --fail-with-body \
--request POST \
--url "https://api.vidgo.ai/api/generate/submit" \
--header "Authorization: Bearer $VIDGO_API_KEY" \
--header "Content-Type: application/json" \
--data "$REQUEST_BODY")
CODE=$(printf '%s' "$RESPONSE" | jq -r '.code // empty')
if [ "$CODE" != "0" ] && [ "$CODE" != "200" ]; then
printf 'API error: %s
' "$RESPONSE" >&2
exit 1
fi
printf '%s
' "$RESPONSE"03
Wait for the result
Query with task_id, continue for not_started/running, and stop for finished/failed. On success, read data.files[].file_url.
Track status
GET https://api.vidgo.ai/api/generate/status/{task_id}Poll about every 2 seconds, then back off gradually. Continue only for not_started or running and stop on finished or failed. You can instead add callback_url to the same top-level request contract.
not_startedrunningfinishedfailedSubmit response
{
"code": 200,
"data": {
"task_id": "ISPBBQG0EATQ452P",
"status": "running",
"created_time": "2026-09-21T11:53:35"
}
}Finished response
{
"code": 200,
"data": {
"task_id": "task-unified-...",
"status": "finished",
"files": [
{
"file_url": "https://storage.vidgo.ai/generated/video.mp4",
"file_type": "video"
}
],
"created_time": "2026-08-22T10:00:00Z",
"progress": 100,
"error_message": null
}
}Complete runnable example
Expand for a complete script with HTTP and business-code checks, task_id validation, polling, terminal-state handling, and a timeout boundary.
Complete runnable example
set -euo pipefail
: "${VIDGO_API_KEY:?Set VIDGO_API_KEY in your environment}"
REQUEST_BODY=$(cat <<'JSON'
{
"model": "kwaivgi/kling-video/ai-avatar/v2/pro",
"input": {
"image_urls": [
"https://cdn.vidgo.ai/apis/models/kwaivgi/kling-video/ai-avatar/v2/pro/v1/03/input.png"
],
"audio_url": "https://cdn.vidgo.ai/apis/models/kwaivgi/kling-video/ai-avatar/v2/pro/v1/03/audio.mp3",
"prompt": "The astronomer speaks calmly and thoughtfully in English, gently opens one hand toward the sky once, then rests it. Subtle wonder in her eyes and a small closing smile. Accurate lip sync, stable face and natural fingers. Preserve twilight lighting, locked camera, no cuts."
}
}
JSON
)
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
--request POST \
--url "https://api.vidgo.ai/api/generate/submit" \
--header "Authorization: Bearer $VIDGO_API_KEY" \
--header "Content-Type: application/json" \
--data "$REQUEST_BODY")
TASK_ID=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.data.task_id // .task_id // empty')
BUSINESS_CODE=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.code // empty')
if [ "$BUSINESS_CODE" != "0" ] && [ "$BUSINESS_CODE" != "200" ]; then
printf 'Submit failed:
%s
' "$SUBMIT_RESPONSE" >&2
exit 1
fi
if [ -z "$TASK_ID" ]; then
printf 'Submit response did not include task_id:
%s
' "$SUBMIT_RESPONSE" >&2
exit 1
fi
START_TIME=$(date +%s)
POLL_DELAY=2
while true; do
if [ $(( $(date +%s) - START_TIME )) -ge 600 ]; then
printf 'Timed out after 600 seconds
' >&2
exit 1
fi
STATUS_RESPONSE=$(curl --silent --show-error --fail-with-body \
--url "https://api.vidgo.ai/api/generate/status/$TASK_ID" \
--header "Authorization: Bearer $VIDGO_API_KEY")
STATUS=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.data.status // .status // empty')
BUSINESS_CODE=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.code // empty')
if [ "$BUSINESS_CODE" != "0" ] && [ "$BUSINESS_CODE" != "200" ]; then
printf 'Status request failed:
%s
' "$STATUS_RESPONSE" >&2
exit 1
fi
case "$STATUS" in
finished)
printf '%s' "$STATUS_RESPONSE" | jq -r '(.data.files // .files // [])[]?.file_url'
break
;;
failed)
printf '%s' "$STATUS_RESPONSE" | jq -r '.data.error_message // .error_message // "Generation failed"' >&2
exit 1
;;
not_started|running)
sleep "$POLL_DELAY"
if [ "$POLL_DELAY" -lt 10 ]; then POLL_DELAY=$((POLL_DELAY + 1)); fi
;;
*)
printf 'Unexpected task status: %s
' "$STATUS" >&2
exit 1
;;
esac
doneInput parameters
These are the fields accepted inside input. The request example shows the required top-level model field.
| Field | Type | Required | Default | Description |
|---|---|---|---|---|
| image_urls | array<string> | Required | — | Exactly one image: public HTTP(S) URL, image Data URI, or raw Base64. |
| audio_url | string | Required | — | Audio must be 2–60 seconds and at most 5 MiB. The server detects its duration. |
| prompt | string | null | Optional | — | Optional text, up to 2,500 characters; surrounding whitespace is trimmed. Empty or null values are omitted. |
Response Fields
Submission returns task identity immediately. Status responses add progress, every output file, or a failure message.
| Field | Type | Description |
|---|---|---|
| code | integer | Application result code; successful responses use 0 or 200. |
| message | string | Human-readable message or error detail when present. |
| data.task_id | string | Task ID used in the status endpoint path. |
| data.status | string | not_started, running, finished, or failed. |
| data.created_time | string | Task creation time in date-time format. |
| data.progress | integer | 0–100 progress when reported by the provider. |
| data.files[] | array | All output files from a successful task, in response order. |
| data.files[].file_url | string | Public URL for a generated video. |
| data.files[].file_type | string | File type, such as video. |
| data.error_message | string | null | Failure detail when status is failed. |
Task Lifecycle
Treat not_started and running as non-terminal states. finished and failed are terminal alternatives; stop polling when either is returned.
not_startedThe task was accepted and is waiting to begin.
runningGeneration is in progress. Continue polling the same task_id.
finishedGeneration succeeded. Read every video URL from data.files[].file_url.
failedGeneration stopped with an error. Read data.error_message and stop polling.
Polling and Errors
- AuthenticationA 401 response means the Bearer API key is missing or invalid. Correct it before retrying.
- ValidationA 400 response identifies an invalid field, unsupported media key, or insufficient credit balance. Correct the request before resubmitting.
- Network and timeoutA transport failure is different from a failed task. Retry status checks with a bounded timeout before deciding that the task failed.
- Polling intervalStart around every 2 seconds and increase the interval gradually for a long-running task.
- Terminal statesContinue only for not_started or running. Stop immediately on finished or failed.
- Callback optionProvide callback_url at the request top level to receive the final flat task object; polling remains available if delivery fails.
Endpoint limits
| Specification | Value | Details |
|---|---|---|
| Input | 1 image + 1 audio | Optional text, up to 2,500 characters; surrounding whitespace is trimmed. Empty or null values are omitted. |
| Audio limits | 2–60s / 5 MiB | Audio must be 2–60 seconds and at most 5 MiB. The server detects its duration. |
| Pricing | 14 credits/sec ($0.070/s) | Final charge uses the server-detected audio duration, rounded up to a whole second. |
Related models
Kling Avatar 2.0 Pro API frequently asked questions
What is the Kling Avatar 2.0 Pro API?
Kling Avatar 2.0 Pro is a Kuaishou Technology (Kling AI) model for high-fidelity talking-avatar video generation from a character portrait and driving audio. It produces digital-human clips with expressive gestures, object-interaction cues, and lifelike eye and neck micro-movements. Built on multimodal grounding and cascaded avatar synthesis, it preserves facial identity across longer narrations while refining broadcast-ready speaking performance. You can call it programmatically or try it from the playground above.
Can I set the output frame rate?
This endpoint does not accept a frame-rate parameter. Check the generated video for its actual frame rate.
Can I set the output resolution?
This endpoint does not accept a resolution parameter. Check the generated video for its actual dimensions.
How does Kling Avatar 2.0 Pro guide gesture interaction?
Add an optional performance prompt to steer pointing, holding, or product-touch cues while the driving audio remains the timing source for speech.
Does Kling Avatar 2.0 Pro refine eye micro-movements?
Yes. Pro emphasizes lifelike gaze shifts and neck dynamics that follow speech phrasing, improving presenter presence beyond basic lip-sync.
What audio duration does Kling Avatar 2.0 Pro accept?
Use a publicly accessible audio file lasting 2–60 seconds and at most 5 MiB. Duration is detected server-side and billed by the rounded-up whole second at 14 credits per second.
When should teams choose Kling Avatar 2.0 Pro delivery?
Choose Pro when a take needs richer gesture guidance, or commercial studio-grade presentation after Standard iteration.