Skip to main content

​
Endpoints

MethodEndpointDescription
POST/api/v1/generateTask/infinitetalkCreate generation task
GET/api/v1/statusTask/infinitetalkQuery task status

​
Authentication

All requests require an API Key in the header: 
Authorization: Bearer YOUR_API_KEY

​
Request Body

{
  "request_type": "async",
  "callback_url": "https://your-server.com/callback",
  "provider": "official",
  "input": {
    "mode": "image-to-video",
    "image_urls": ["https://example.com/portrait.png"],
    "audio_urls": ["https://example.com/voice.mp3"],
    "prompt": "keep the face stable while syncing lips to the audio",
    "resolution": "480p",
    "seed": -1
  }
}

​
Parameters

​
request_type
string
default:"async"
async (polling) or callback (webhook)
​
callback_url
string
Callback URL, required when request_type=callback (conditional)
​
provider
string
default:"auto"
Routing strategy: auto, value, or official
​
input
object
required
Model input parameters

​
Example

curl -X POST "https://api.apixo.ai/api/v1/generateTask/infinitetalk" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "callback",
    "callback_url": "https://your-server.com/callback",
    "provider": "official",
    "input": {
      "mode": "image-to-video",
      "image_urls": [
        "https://example.com/portrait.png",
        "https://example.com/mask.png"
      ],
      "audio_urls": [
        "https://example.com/voice.mp3"
      ],
      "prompt": "keep the face stable while syncing lips to the audio",
      "resolution": "720p",
      "seed": 7
    }
  }'

​
Response

​
POST /api/v1/generateTask/infinitetalk

Returns taskId on success for subsequent status queries. Success: 
{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678"
  }
}
Error: 
{
  "code": 400,
  "message": "Insufficient credits",
  "data": null
}

​
GET /api/v1/statusTask/infinitetalk

Query task execution status and results via taskId. 
curl -X GET "https://api.apixo.ai/api/v1/statusTask/infinitetalk?taskId=task_12345678" \
  -H "Authorization: Bearer YOUR_API_KEY"
Success: 
{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "success",
    "resultJson": "{\"resultUrls\":[\"https://r2.apixo.ai/video.mp4\"]}",
    "createTime": 1767965610929,
    "completeTime": 1767965652317,
    "costTime": 41388
  }
}
Failed: 
{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "failed",
    "failCode": "CONTENT_VIOLATION",
    "failMsg": "Content does not meet safety guidelines"
  }
}

​
Status Response Fields

​
taskId
string
Unique task identifier.
​
state
string
Current task state: pending, processing, success, or failed.
​
resultJson
string
JSON string containing resultUrls array. Only present on success. Parse with JSON.parse().
​
failCode
string
Error code. Only present when state is failed. See Error Codes.
​
failMsg
string
Human-readable error message. Only present when state is failed.
​
createTime
integer
Task creation timestamp (Unix milliseconds).
​
completeTime
integer
Task completion timestamp (Unix milliseconds).
​
costTime
integer
Processing duration in milliseconds.

​
Error Codes

CodeDescription
400Invalid parameters or request error
401Invalid or missing API Key
429Rate limit exceeded
Fail CodeDescription
CONTENT_VIOLATIONContent violates safety guidelines
INVALID_IMAGE_URLCannot access provided image URL
INVALID_AUDIO_URLCannot access provided audio URL

​
Rate Limits

LimitValue
Requests10000 / minute
Concurrent tasks1000
Exceeding limits returns 429 error. Wait and retry.

​
Tips

  • Mode: Only image-to-video is supported. Provide one portrait image and one audio file.
  • Audio requirements: Must be a public MP3, WAV, or M4A URL, up to 128 MB and 10 minutes.
  • Billing: Per-second billing based on actual audio duration. Minimum charge is 5 seconds.
    • 480p: $0.03/second
    • 720p: $0.06/second
  • Mask image: Optionally provide a second image in image_urls to specify which regions can move. Do not use the full image as a mask — it may render as fully black.
  • Prompt tips: Keep prompts short and in English. Too many prompts may cause noisy or unexpected results.
  • Processing time: Approximately 10–30 seconds of wall time per 1 second of video output (varies by resolution and queue).
  • Callback mode: Video generation can take minutes for long audio; strongly recommend callback mode for production.
  • Video expiration: Result URLs are valid for 15 days. Download promptly.
  • Seed: Set a fixed seed (0–2147483647) for reproducible results, or use -1 for random.
InfiniteTalk generates variable-length videos — billing is per second of audio duration (minimum 5 seconds). Use callback mode for production workloads. Result URLs expire after 15 days; download important outputs promptly.