Remove Background Music from Voice Recording

Why this matters

Re-recording a voiceover because a music bed leaked in costs time and sounds different. Source separation recovers the original vocal take instead.

Trained separation models isolate the speech stem while preserving prosody — the result is the voice, minus the bed, not an EQ'd mush.

How it works

Submit the recording with stems=[vocals]. The API returns the isolated speech track plus the music stem, both in WAV/FLAC.

Submit a job with an input URL (S3, GCS or HTTPS), poll the job URL, and download the rendered output. No GPU, no queues, no ffmpeg builds to babysit.

Code

import requests, time

API = "https://api.mlslabs.io/v1/vocal-separator/jobs"
headers = {"X-API-Key": "YOUR_API_KEY"}
payload = {"input": "s3://bucket/voiceover.wav", "stems": ["vocals"]}

resp = requests.post(API, json=payload, headers=headers)
job = resp.json()
while job["status"] not in ("succeeded", "failed"):
    time.sleep(3)
    job = requests.get(job["url"], headers=headers).json()

print("Output:", job["output_url"])

Pro tips

• Separate before any heavy compression — less aggressive processing upstream means cleaner stems.
• Use the vocals stem in your podcast editor; keep the music stem for re-mixing.
• For meeting recordings, pair with denoise for the cleanest transcript.

Run the Vocal Separator collection — voiceover sample prefilled.