| Mode (type) | Output tracks | Typical usage | Point consumption |
|---|---|---|---|
separate_vocal (default) | 2 tracks - vocals + accompaniment | Quick vocal separation, karaoke, basic mixing | 10 points |
split_stem | Up to 12 tracks - vocals, harmonies, drums, bass, guitar, keyboard, strings, brass, woodwind, percussion, synthesizer, FX/other; | Advanced mixing, remixing, sound design, single instrument extraction | 50 points |
split_stem_advanced | Up to 12 tracks - same as split_stem, and can precisely separate individual target tracks by specifying stemName | Single instrument extraction, fine post-production | 20 points |
| Name | Type | Description |
|---|---|---|
taskId | string | The ID of the original music generation task |
audioId | string | When there are multiple versions, specify the audio variant to be processed |
type | string | Separation mode: separate_vocal, split_stem, or split_stem_advanced; default separate_vocal |
stemName | string | Only effective when type is split_stem_advanced; used to specify the name of a single audio track/instrument; |
separate_vocal returns 2 tracks - vocals + accompaniment.split_stem returns up to 12 separate audio tracks - vocals, harmony, drums, bass, guitar, keyboard, strings, brass, woodwind, percussion, synthesizer, FX/other.split_stem_advanced supports precise extraction of a single target audio track by specifying stemName.curl --location 'https://api.kie.ai/api/v1/vocal-removal/generate' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"taskId": "5c79****be8e",
"audioId": "e231****-****-****-****-****8cadc7dc",
"callBackUrl": "https://api.example.com/callback",
"type": "separate_vocal"
}'{
"code": 200,
"msg": "success",
"data": {
"taskId": "5c79****be8e"
}
}