{"info":{"title":"deezer/spleeter","version":"1.0.0"},"paths":{"/":{"post":{"summary":"Separate","responses":{"200":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/Output"}}},"description":"Successful Response"}},"operationId":"deezer_spleeter_separate","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/Input"}}},"required":true}}}},"openapi":"3.1.0","components":{"schemas":{"Input":{"type":"object","title":"Input","required":["audio"],"properties":{"audio":{"type":"string","title":"Audio","format":"uri","x-order":0,"description":"URL of the track to split. Built for a full-band music mix with the lead vocal present - a solo vocal, or a track that is already instrumental, has nothing to separate. WAV and MP3 sources both decode. Keep it to a single song: runs up to 3.5 minutes are verified and about five minutes is the practical ceiling. An over-long file FAILS the whole request - sometimes with no error message at all - rather than returning a shortened result; a failed request is not charged."}}},"Output":{"type":"array","items":{"type":"string","format":"uri"},"title":"Output","maxItems":2,"minItems":2,"description":"The two separated tracks as URLs, always in this order: index 0 is the ACCOMPANIMENT - the full mix with the lead vocal removed, i.e. the instrumental or backing track - and index 1 is the ISOLATED VOCAL. Both are WAV files, the full length of the input and at the input's own sample rate. Both are band-limited: the separation model was trained on spectrograms up to 11 kHz, so content above that is not reproduced in either stem."}}}}