Vocal Remover audio separation API

Choose a completed generated track and use its task_id and audio_id to request audio separation. The existing online form starts with the vocal-and-instrumental workflow; the API also accepts separate_type to select the documented processing direction. Retrieve the completed track information, listen to each returned component alongside the original and retain the files for editing, arrangement review or a music project that needs separated material.

Listen to each returned audio component and compare important passages with the source recording. Select the available tracks that suit your editing or arrangement task, then import them into your audio project. Save each returned file URL with its track label, source identifiers and separation request so you can identify the material used in later work.

Submit model: separate-vocals with input.task_id and input.audio_id. Include separate_type when selecting the accepted separation option. Save the processing task_id, query music details and inspect the returned separation data and audio URLs for that source.

Use separate_type: separate_vocal for the default vocal-and-accompaniment workflow. The current interface also accepts split_stem for multitrack processing. The online form submits the default option; to prepare the other accepted option, add separate_type explicitly in JSON mode. Check the actual completed track list when assigning the returned components to your project.

Use the completed source task_id and the selected candidate audio_id. The API accepts separate_type: separate_vocal for the default vocal-and-instrumental operation and split_stem for its stem-processing option. The existing form submits the default; use JSON mode to include the explicit field when preparing another accepted option. Inspect the actual returned track list before assigning roles in your project.

Prepare a completed generated track from your account, its source task_id and the audio_id of the exact candidate to process. Keep the original audio URL for listening and identify the passages or musical parts you want to review after separation.

Read this page’s dynamic pricing section for the current task rate per processing request. Source music generation and other follow-up operations use their own rates. Review the current price before submitting, and retain the completed result and task association when planning additional work.

The current task uses model: separate-vocals with the accepted separate_type choices. The online form starts with the default vocal separation. The documentation also describes dedicated stem-split and upload-based operations; those use their own model identifiers and source requirements. Choose the operation from its required source and inspect the returned track data before treating it as a particular stem set.

Listen to each returned component and compare it with the original recording. Inspect the vocal, accompaniment or other available parts for the material you intend to reuse, and review the audible separation around important passages. Preserve the original audio and returned track URLs when preparing an edit or arrangement.