Separate audio
Submit a prompt-based audio separation request with a public URL or uploaded file.
Use POST /v1/queue/audio/separate to submit an async separation job.
Public URL input
curl -X POST https://audiolasso.dev/v1/queue/audio/separate \
-H "Authorization: Bearer $AUDIOLASSO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"audio_url": "https://example.com/session.wav",
"prompt": "separate the piano from the background music"
}
}'audio_url must be a public HTTPS URL. Localhost, private network URLs, and file:// URLs are rejected.
Uploaded file input
Use file_id when the source file is local or private:
{
"input": {
"file_id": "file_01jabc",
"prompt": "isolate the lead vocal"
}
}See Upload local files for the upload flow.
Prompt guidance
Be specific about the sound you want in the target track.
Good prompts:
isolate the lead vocalseparate the piano from the rest of the songremove crowd noise and keep the speakerextract the dog bark from the street recording
Weak prompts:
clean thismake betterremove noise
Response
The submit endpoint returns 202 Accepted with status, stream, and result URLs.
{
"request_id": "req_01jabc",
"status": "IN_QUEUE",
"model": "audio/separate",
"created_at": "2026-04-25T08:00:00.000Z",
"status_url": "https://audiolasso.dev/v1/queue/requests/req_01jabc/status",
"stream_url": "https://audiolasso.dev/v1/queue/requests/req_01jabc/status/stream",
"result_url": "https://audiolasso.dev/v1/queue/requests/req_01jabc/result"
}