Separate Audio Stems

Separate a recording of at most 3600 seconds into six stems with ElevenLabs six_stems_v1: vocals, drums, bass, guitar, piano and other. Upload the audio through the asset upload API (at most 200 MB) and pass its asset_id. The request waits for the stems and answers 200 with a time-limited mp3 url for each, every stem the full length of the audio. Each request is priced per second of the audio. A request the workspace's API credits cannot cover is refused with 402 insufficient_credit before the model runs. The credits are charged once the stems are made, and a failed separation is not charged. If the balance no longer covers the charge when the stems are ready, the request answers 402 insufficient_credit without them. Send an Idempotency-Key header with every request: it is required. Repeating a request with the same key and body returns the original stems with fresh URLs without charging again, a duplicate sent while the original is still running gets 409 request_in_progress, and the same key with a different body gets 409 conflict. Failed requests replay their stored error; use a new key for a new attempt.