Multistem Splitter API
Extract multiple stems from one source audio file in a single async audio task.
Multistem Splitter API
Use audio-multistem to extract up to six supported stems from one public
audio URL.
Endpoint
POST /api/v1/audio/generationsPoll completion with:
GET /api/v1/tasks/{id}Example
curl https://reapi.ai/api/v1/audio/generations \
-H "Authorization: Bearer $REAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "audio-multistem",
"audio_url": "https://cdn.example.com/song.wav",
"stem_list": ["vocals", "drum", "bass"],
"encoder_format": "mp3"
}'Parameters
| Field | Type | Required | Notes |
|---|---|---|---|
model | string | yes | Use audio-multistem. |
audio_url | URL | yes | Public HTTP(S) source audio URL. |
stem_list | enum[] | yes | 1-6 values: vocals, drum, piano, bass, electric_guitar, acoustic_guitar. |
splitter | enum | no | auto, andromeda, perseus, orion, phoenix, lyra, or lynx. auto is omitted upstream so the default engine is used. |
extraction_level | enum | no | deep_extraction or clear_cut. Defaults to deep_extraction. |
dereverb_enabled | boolean | no | Enable dereverb cleanup. |
encoder_format | enum | no | mp3, wav, flac, aac, or ogg. |
Output
Completed tasks return output.audio_urls and, when available, labeled
output.tracks.
Multistem jobs are billed per rounded-up source minute, multiplied by the selected stem count. See current rate on the Multistem Splitter model page.