reAPI DocsVocal Remover API
Remove or isolate vocals from a public audio URL with the async reAPI audio endpoint.
Vocal Remover API
Use audio-stem-separator with stem: "vocals" to isolate vocals and receive
downloadable audio tracks through the universal task flow.
Endpoint
POST /api/v1/audio/generationsPoll the returned task:
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-stem-separator",
"audio_url": "https://cdn.example.com/song.wav",
"stem": "vocals",
"encoder_format": "mp3"
}'Parameters
| Field | Type | Required | Notes |
|---|---|---|---|
model | string | yes | Use audio-stem-separator. |
audio_url | URL | yes | Public HTTP(S) source audio URL. |
stem | enum | yes | Use vocals for this API page. |
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. |
multivocal | string | no | lead_back. Only valid with stem: "vocals". |
dereverb_enabled | boolean | no | Enable dereverb cleanup. |
encoder_format | enum | no | mp3, wav, flac, aac, or ogg. |
Output
Completed tasks return output.audio_urls. When labels are available,
output.tracks includes type, label, and url for each track.
Audio jobs are billed at 200 credits ($0.20) per rounded-up source minute.