stemNameMode (type) | Returned Stems | Typical Use Cases | Credit Cost |
|---|---|---|---|
separate_vocal (default) | 2 stems — Vocals + accompaniment | Quick vocal removal, karaoke, and basic mixing | 10 credits |
split_stem | Up to 12 stems — Vocals, backing vocals, drums, bass, guitar, keyboard, strings, brass, woodwinds, percussion, synthesizer, FX/other; | Advanced mixing, remixing, sound design, and individual instrument extraction | 50 credits |
split_stem_advanced | Up to 12 stems — Same as split_stem, with support for specifying a single target stem through stemName for precise separation | Individual instrument extraction and detailed post-production | 20 credits |
| Name | Type | Description |
|---|---|---|
taskId | string | The ID of the original music generation task |
audioUrl | string | Public URL of an audio file (max 20 MB). Use it alone; cannot be combined with taskId or audioId. |
audioId | string | Specifies the audio variant to process when multiple versions exist. Cannot be used together with audioUrl. |
type | string | Separation mode: separate_vocal, split_stem, or split_stem_advanced; defaults to separate_vocal |
stemName | string | Takes effect only when type is split_stem_advanced (required there); specifies the name of the individual stem/instrument to separate; |
separate_vocal returns 2 stems — vocals + accompaniment.split_stem returns up to 12 independent stems — vocals, backing vocals, drums, bass, guitar, keyboard, strings, brass, woodwinds, percussion, synthesizer, and FX/other.split_stem_advanced supports specifying a single target stem through stemName for precise extraction.POST /api/v1/client/tasks request with model: "suno/separate-vocals" and the parameters above inside input. Provide exactly one audio source: taskId + audioId, audioId alone (a Suno audio ID), or audioUrl.vocal_url, instrumental_url and other per-stem URL fields, plus an origin_data list (each item has id, stem_type_group_name, audio_url, duration). Use an origin_data[].id as audioId for Generate MIDI from Audio.curl --location 'https://api.emix.ai/api/v1/client/tasks' \
--header 'Content-Type: application/json' \
--data '{
"model": "suno/separate-vocals",
"callBackUrl": "https://api.example.com/callback",
"input": {
"taskId": "5c79****be8e",
"audioId": "e231****-****-****-****-****8cadc7dc",
"type": "separate_vocal"
}
}'{
"code": 200,
"msg": "success",
"data": {
"taskId": "5c79****be8e"
}
}