Skip to main content
Real-time automated analysis of live video frames & audio to surface or auto-enforce against policy violations with minimal latency. Use this guide to enable, configure thresholds, act on incidents, and continuously tune signal quality.

Enable the Feature

1

Request Access

Contact support to enable livestream moderation.
2

Provisioning

Support confirms activation; feature appears in Console settings.
3

Shadow Phase (Recommended)

First 1–2 weeks: log results but keep automatic termination conservative.

Enable

Provision & price

Configure

Per-category thresholds

Monitor

Status & incident volume

Intervene

Stop / Delete streams

Tune

Threshold calibration

Audit

Review false positives

How Detection Works

The system continuously samples frames (and audio signals where applicable) and classifies content into risk categories. Each detection produces category confidence scores (0–100%). Your configured thresholds decide whether a stream:

Detection Categories

Explicit sexual imagery/acts. Maintain strict thresholds to minimize exposure risk.
Graphic violence or severe physical harm. Sensitivity may vary by regional norms.
Illegal / compliance restricted material (e.g., weapons, contraband). Low tolerance.
Borderline or contextual material. Often noisier—calibrate carefully to reduce review overload.
Offensive language or slurs (audio/overlays). Tune to community standards.

Configuring Confidence Thresholds

Two thresholds per category: Flagged (human review) and Terminated (auto-stop). Flagged <= Terminated must always hold.
A threshold of 0 (or extremely low) will flood the queue with low-confidence matches, overwhelming moderators and increasing costs.

Tuning Playbook

Flag queue FPR > 30% or moderator backlog growing & SLA breach risk.
Confirmed late detections or missed early intervention opportunities.
Any unjustified auto-termination (precision drop) or creator complaints validated.
Severe violations frequently only reaching Flagged state; evidence of slow manual response.
Temporarily widen only the lowest-signal category (e.g., Inappropriate) while holding strict categories steady.

Acting on Incidents

Open flagged stream → verify frame samples → Decide: Stop, Delete, or Allow.

Key Metrics

Best Practices

Run with only Flagged actions (no Terminated) for initial calibration if risk appetite allows.
Adjust one category per cycle to attribute impact.
Retain representative false positives & misses for model feedback.
Provide clear examples per category to align decisions & reduce subjective variance.
Publish community guidelines emphasizing live content do’s & don’ts.

Troubleshooting

Next Steps

Moderation Feed

Central triage & audit

User History

Broadcaster behavioral context