AI Avatar

AI Avatar Pro

Portrait + audio → HD lip-synced talking video, up to 35s (720 / 1280 / 1536px)

AI Avatar Pro turns one portrait photo + one audio clip into a lip-synced talking video, with an optional motion prompt, up to 1536px and 35 seconds. Async task; poll for status after submitting.

Base URL: https://api.aiclonevoicefree.com | Auth: Authorization: Bearer sk_...

POST /api/v2/avatar/generate

FieldTypeRequiredNotes
image_urlstringPortrait photo URL
audio_urlstringSpeech audio URL
durationint5/10/15/20/25/30/35, or 0 = follow full audio; default 10
audio_duration_secondsnumberAudio length (s), used for billing when duration=0
resolutionintLong-edge pixels 720 / 1280 / 1536; default 1280
framerateint24 / 25 / 30; default 25
motion_promptstringMotion/expression description, ≤ 2000 chars; a default "speaking naturally" prompt is used if empty

Billing (video credits, per second)

Long-edge resolutionPer-second rate
7201.5
12802
15362.5

cost = ceil(per-second rate × billable seconds). Billable seconds = duration when duration > 0, otherwise audio_duration_seconds (capped at 35s). 402 at submit if video credits are insufficient; auto-refunded on failure.

Examples

  • 1280px, 10s = 2 × 10 = 20 credits
  • 1536px, 20s = 2.5 × 20 = 50 credits

Example

curl -X POST https://api.aiclonevoicefree.com/api/v2/avatar/generate \
  -H "Authorization: Bearer sk_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "image_url": "https://your-cdn.com/portrait.png",
    "audio_url": "https://your-cdn.com/speech.mp3",
    "duration": 10,
    "resolution": 1280,
    "framerate": 25,
    "motion_prompt": "speaking to the camera naturally with subtle expressions and head movement"
  }'

Response 202

{
  "task_id": "1939...",
  "status": "pending",
  "capability": "avatar",
  "action": "generate",
  "model": "avatar-pro"
}

Getting the result

Poll GET /api/v2/avatar/tasks/{task_id}; when done:

{
  "status": "completed",
  "capability": "avatar",
  "model": "avatar-pro",
  "progress": 1.0,
  "videoUrl": "https://.../result.mp4"
}

Generation usually takes several minutes. See also AI Avatar and Dual Avatar.

On this page