Add Vocals (Overpainting)

Endpoint

POST /api/v1/music/add-vocals

Asynchronous. Returns a task_id. Poll Get Task for results. Takes an existing clip and “paints” new vocal content over a specified time range using a sample source clip as the vocal reference.

Request body

Field	Type	Required	Description
`chop_sample_clip_id`	string	Yes	Clip ID of the vocal sample source.
`chop_sample_start_s`	float	No	Start time (seconds) in the sample clip. Default `0`.
`chop_sample_end_s`	float	No	End time (seconds) in the sample clip. Default: full clip.
`prompt`	string	No	Lyric content for the new vocal section. Supports Chinese and English.
`tags`	string	No	Style tags (e.g. `"流行女声"` or `"pop female"`).
`mv`	string	No	Model version override.
`callback_url`	string	No	Webhook URL for completion notification. See Webhooks.
`retention_days`	integer	No	Days to retain audio files. Default `7`.

Response

{
  "code": 0,
  "message": "ok",
  "request_id": "req-1710000000000",
  "data": {
    "task_id": "64f3a1b2c8d9e0f1a2b3c4d5",
    "status": "queuing"
  }
}

Example

curl -X POST https://api.example.com/api/v1/music/add-vocals \
  -H "Authorization: Bearer sk-mm-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "chop_sample_clip_id": "abc123def456",
    "chop_sample_start_s": 10.0,
    "chop_sample_end_s": 25.0,
    "prompt": "[副歌]\n在这片土地上\n我找到了归宿",
    "tags": "流行 抒情"
  }'

Getting Started

Overview

Music Generation

Lyrics

Audio Processing

AI Singer (Persona)

Tasks & Results

Endpoint

Request body

Response

Example

​Endpoint

​Request body

​Response

​Example

Endpoint

Request body

Response

Example