Skip to main content
POST
/
api
/
v1
/
generate
/
generate-persona
Generate Persona
curl --request POST \
  --url https://api.kie.ai/api/v1/generate/generate-persona \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "taskId": "5c79****be8e",
  "audioId": "e231****-****-****-****-****8cadc7dc",
  "name": "Electronic Pop Singer",
  "description": "A modern electronic music style pop singer, skilled in dynamic rhythms and synthesizer tones",
  "vocalStart": 12.5,
  "vocalEnd": 25.8,
  "style": "Electronic Pop"
}
'
{
  "code": 200,
  "msg": "success",
  "data": {
    "personaId": "a1b2****c3d4",
    "name": "Electronic Pop Singer",
    "description": "A modern electronic music style pop singer, skilled in dynamic rhythms and synthesizer tones"
  }
}

​
Usage Guide

  • Use this endpoint to create Personas (music characters) for generated music
  • Requires the taskId from music generation related endpoints (generate, extend, cover, upload-extend, mashup) and audio ID
  • Customize the Persona name and description to give music unique personality
  • Generated Personas can be used for subsequent music creation and style transfer

​
Parameter Details

  • taskId: Required parameter, can be obtained from the following endpoints:
  • audioId: Required parameter, specifies the audio ID to create Persona for
  • name: Required parameter, assigns an easily recognizable name to the Persona
  • description: Required parameter, describes the Persona’s musical characteristics, style, and personality

​
Developer Notes

  • Important: Ensure the music generation task is fully completed before calling this endpoint. If the music is still generating, this endpoint will return a failure
  • Model Requirement: Persona generation only supports taskId from music generated with models above v3_5 (v3_5 itself is not supported)
  • It is recommended to provide detailed descriptions for Personas to better capture musical characteristics
  • The returned personaId can be used in subsequent music generation requests to create music with similar style characteristics
  • You can apply the personaId to the following endpoints:
  • Each audio ID can only generate a Persona once

​
Parameter Example

{
  "taskId": "5c79****be8e",
  "audioId": "e231****-****-****-****-****8cadc7dc",
  "name": "Electronic Pop Singer",
  "description": "A modern electronic music style pop singer, skilled in dynamic rhythms and synthesizer tones"
}
Ensure that the music generation task corresponding to the taskId is complete and the audioId is within the valid range.
Providing detailed and specific descriptions for Personas helps the system more accurately capture musical style characteristics.

Authorizations

​
Authorization
string
header
required

All APIs require authentication via Bearer Token.

Get API Key:

  1. Visit API Key Management Page to get your API Key

Usage: Add to request header: Authorization: Bearer YOUR_API_KEY

Note:

  • Keep your API Key secure and do not share it with others
  • If you suspect your API Key has been compromised, reset it immediately in the management page

Body

application/json
​
taskId
string
required

Unique identifier of the original music generation task. This can be a taskId returned from any of the following endpoints:

  • Generate Music (/api/v1/generate)
  • Extend Music (/api/v1/generate/extend)
  • Upload And Cover Audio (/api/v1/generate/upload-cover)
  • Upload And Extend Audio (/api/v1/generate/upload-extend)
  • Generate Mashup Music (/api/v1/generate/mashup)
Example:

"5c79****be8e"

​
audioId
string
required

Unique identifier of the audio track to create Persona for. This ID is returned in the callback data after music generation completes.

Example:

"e231****-****-****-****-****8cadc7dc"

​
name
string
required

Name for the Persona. A descriptive name that captures the essence of the musical style or character.

Example:

"Electronic Pop Singer"

​
description
string
required

Detailed description of the Persona's musical characteristics, style, and personality. Be specific about genre, mood, instrumentation, and vocal qualities.

Example:

"A modern electronic music style pop singer, skilled in dynamic rhythms and synthesizer tones"

​
vocalStart
number
default:0

Start time (in seconds) for Persona analysis segment extraction. Used to specify the time point in the audio from which to extract the segment for Persona analysis. Must be less than vocalEnd, and vocalEnd - vocalStart must be between 10–30 seconds. Defaults to 0.0.

Required range: x >= 0Must be a multiple of 0.01
Example:

12.5

​
vocalEnd
number
default:30

End time (in seconds) for Persona analysis segment extraction. Together with vocalStart, used to specify the time range for analysis. vocalEnd - vocalStart must be between 10–30 seconds. Defaults to 30.0.

Required range: x >= 0Must be a multiple of 0.01
Example:

25.8

​
style
string

Optional. Used to supplement the description of the music style tag corresponding to the Persona, such as "Electronic Pop", "Jazz Trio", etc.

Example:

"Electronic Pop"

Response

Request successful

​
code
enum<integer>

Response Status Codes

  • 200: Success - Request has been processed successfully
  • 401: Unauthorized - Authentication credentials are missing or invalid
  • 402: Insufficient Credits - Account does not have enough credits to perform the operation
  • 404: Not Found - The requested resource or endpoint does not exist
  • 409: Conflict - Persona already exists for this music
  • 422: Validation Error - The request parameters failed validation checks
  • 429: Rate Limited - Request limit has been exceeded for this resource
  • 451: Unauthorized - Failed to fetch the music data. Kindly verify any access limits set by you or your service provider
  • 455: Service Unavailable - System is currently undergoing maintenance
  • 500: Server Error - An unexpected error occurred while processing the request
Available options:
200,
401,
402,
404,
409,
422,
429,
451,
455,
500
​
msg
string

Error message when code != 200

Example:

"success"

​
data
object