Audio Splitter

Separates an audio clip into two tracks: the foreground (voice) and the background. Use it to isolate speech before analysis or review. This is a utility, not a detector: it gives no real or fake verdict.

Slug	ID	Status	Tagged	Model version
`audio-splitter`	`10`	Active	No	Not reported

Request

Slot	Accepted `contentType`
`original`	`audio/mpeg`, `audio/wav`, `audio/m4a`

{
  "taskTypeId": "10",
  "inputs": [
    { "slotName": "original", "fileName": "call.wav", "contentType": "audio/wav", "sizeBytes": 2097152 }
  ]
}

See Running a job for the full create, upload and finalize flow.

Limits

File size: up to the account upload limit, 10 MB by default.

Result

The separated tracks are delivered as files, not in result. result holds foreground and background paths that are internal to the worker and can't be downloaded; use the artifacts below.

Output artifacts

`kind`	`contentType`	`metadata.type`	Description
`audio`	`audio/wav`	`foreground`	The voice track
`audio`	`audio/wav`	`background`	Everything else

Download them from artifacts on GET /jobs/{id}, picking each track by metadata.type.

Cost and availability

Fixed price per job, set by your plan. The exact amount is returned as cost when you create the job. See Quotas & Credits.
Available on the cloud API; your plan decides which task types you can use.