Spatial Audio for Livestreams

Why this matters

Live events are the flagship spatial-audio use case: the room, the crowd, the stage. Upmixing the broadcast stereo feed into 5.1/Atmos in real time adds the immersion without a second mixing desk.

Low-latency upmixing is a different beast than offline: the model must run on a live frame budget.

How it works

Point the API at your live stereo feed with mode=live; it outputs a spatialized 5.1/7.1.2 stream with sub-second added latency.

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/ai-mixing/jobs"
headers = {"X-API-Key": "YOUR_API_KEY"}
payload = {"input": "rtmp://ingest.example.com/live/feed", "output": "5.1", "mode": "live"}

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

• Start with 5.1 for the live feed — Atmos objects in live are harder for legacy decoders.
• Keep a stereo fallback; not every device decodes spatial.
• Test the full chain (encoder → player) with your CDN before show day.

Model the live spatial flow in Postman.