Questions I keep getting, with the answers I'd actually give a friend.

On a stable nightstand 1.5–3 feet (50–90 cm) from your head, microphone facing toward you, plugged in, with Do Not Disturb on. Don't put it under a pillow or blanket.

Yes — keep the phone on charge. SomniSense uses about 8–12% battery per 8 hours, but a full overnight session benefits from being plugged in.

The model is trained to focus on the loudest, closest source. If you share a bed, place the phone slightly closer to the person being monitored. We are not currently designed for two-person monitoring.

Yes. The first 3 nights establish your baseline — you'll see scores, but trend signals only become reliable after that. If you want to run a Lifestyle Lab™ experiment (e.g., a side-sleep test), plan for 14 nights of tagged data.

No. Tagging is optional. You can skip the pre-sleep dialog and SomniSense will still monitor and produce a normal report. But the Lifestyle Lab™ Factor Impact analysis only works if you tag.

For snoring: 91% detection rate, 98.5% precision. For breathing pauses: 80% detection rate, 91% precision. BRI agrees with clinical AHI within ±5 events/hour for 87% of nights at AHI ≤ 30. Validation: n=70+ paired nights vs in-lab polysomnography. See /accuracy for full methodology.

We use a precision-first detection mode by design. We'd rather miss a borderline event than falsely alarm you. If you suspect undercounting, your true per-hour event count is most likely the same as or higher than the displayed BRI — never significantly lower.

No. SomniSense is a wellness and self-monitoring tool, not a medical device. It does not diagnose any condition. SomniSense reports a Breathing Irregularity Index (BRI) — the same per-hour metric clinicians call AHI in medical literature — but a BRI score is data, not a diagnosis. If your BRI is repeatedly elevated, please see a sleep specialist.

iPhone running iOS 14 or later, Android running Android 10 or later. Mid-range phones from 2019 onward run the on-device model fine.

Yes. Every detected event in the report has a play button next to its waveform. Tap it and you'll hear the actual audio that the AI classified — the snore, the silence, the gasp. Free users get 3 audio plays per report; Pro is unlimited.

No, not by default. All AI analysis happens on your device. Audio only leaves your phone if you explicitly tap Export or Share.

Anonymous app analytics (crashes, feature usage), and the metrics needed to render your reports — never the audio itself, unless you explicitly opt in to a future cloud-sync feature.

Yes. In Profile → Data Management, you can delete every recording, every report, and your account, anywhere, anytime.

Yes. See /legal/privacy for the full data inventory and your rights.

No. We don't sell data. We don't share data with advertisers. Our business is the subscription.

Yes. You can cancel anytime in the first 7 days and you will not be charged. After day 7, the plan you selected (monthly or annual) begins.

The first 7 days are free. After that, $7.99 per month, or $49.99 per year (≈ $4.17/month, save 48%). Cancel through the App Store or Google Play before day 7 and you won't be charged.

Through the Apple App Store (Settings → Subscriptions) or Google Play (Profile → Payments & subscriptions). Pro features remain active until the end of your current billing period.

We don't give medical advice. SomniSense's BRI uses the same per-hour event-rate scale clinicians call AHI, so a BRI of 18 corresponds to what they would describe as "moderate" range. As a general rule, a BRI consistently above 15 warrants a conversation with a sleep specialist. SomniSense data — your tagged nights, your audio clips, your trend — can be a useful starting point for that visit.

The model has not been validated for users under 18. We don't recommend it for children.

SomniSense can monitor residual events, but if your CPAP machine produces a compliance report, that report is more authoritative for treatment decisions.