Cover callbacks

How AI Cover and Cover voice requests deliver their result to your callbackUrl, and which other products use a different mechanism.

_{AI Cover · Workflow: AI Cover quickstart}

This callback protocol applies only to the AI Cover flows that take a callbackUrl:

webhookType	Started by
TRAIN_COVER_SPEAKER	Create a Cover voice
EDIT_COVER_SPEAKER	Improve a Cover voice
COVER_SONG	Generate a cover

These requests take longer to process, so the result is delivered asynchronously to the callback URL you provide in the request.

Other products do not use this protocol:

• Speech to Text — Batch: poll the transcription. The optional completion notification has its own signed (HMAC) contract; see STT completion notifications.
• Speech to Text — Real-time: results arrive as WebSocket events on the session’s socket. They are not HTTP callbacks; see the real-time quickstart.
• Text to Music and Interpretation: poll-based; no callback (see below).
• Text to Speech, TTS voices and account information: the result is in the HTTP response.

Request

Please provide a callback URL and ensure that the callback URL provided is consistent across different scenarios.

Please make sure that the url you provide is accessible to the public network and that the request type is POST.

If the callback URL varies, there may be inconsistencies between the callback URL used during the callback and the callback URL you provided at the time of the request.

Response

When an asynchronous request is sent successfully, we will immediately provide a webhookId. When a callback is made, this webhookId will also be included in the callback URL. You can use the webhookId to associate the request with the callback.

webhookId · string

When the request is successfully sent, a webhookId will be synchronously returned. The same information will also be called back in the callbackUrl, which is used to correlate the request and the response.

webhookType · string

TRAIN_COVER_SPEAKER: Add an AI Cover Voice

EDIT_COVER_SPEAKER: Improve an AI Cover Voice

COVER_SONG: Create an AI Cover song

status · string

The status of this request

summary · string

Human-readable result summary.

data · Object

business data

Samples

200（success）

{
    "webhookId":"1700189306ffhdkejwcsk2",
    "webhookType":"TRAIN_COVER_SPEAKER",    
    "status":"SUCCESS",  
    "summary":"Clone training success.",  
    "data":{
        "id":"100"
    }
}

200（fail）

{
    "webhookId":"1700189306ffhdkejwcsk2",
    "webhookType":"TRAIN_COVER_SPEAKER",    
    "status":"FAILURE",  
    "summary":"Clone training failed."
}

Text-to-Music and Interpretation

The callback and webhookId mechanism on this page applies to the AI Cover flows listed above (TRAIN_COVER_SPEAKER, EDIT_COVER_SPEAKER, COVER_SONG).

Text-to-Music and Interpretation do not use callbacks and never call your webhook. They are poll-based: create the project, then poll the project/job endpoints until the resource reaches a terminal state. Neither product takes a callback URL parameter, and neither returns a webhookId.

If you are integrating Text-to-Music or Interpretation, implement polling instead — see Async jobs, polling and retries.

Text-to-Music quickstart

Poll the project until projectStatus is READY, then download the MP3.

Interpretation quickstart

Poll the project until every target is READY, then play or export it.