HOW IT WORKS · WRITTEN BY THE PERSON WHO BUILT IT
Your phone, your bed, your data — that's it.
No wearable, clinic appointment, or subscription is required to review the Free basics. Here is exactly what happens between tonight and tomorrow morning, from setup to the evidence you can inspect.
Put your phone on the nightstand, optionally tag what is true tonight, and start a session. The on-device AI analyzes snore-like and breathing-irregularity-like acoustic patterns without uploading sleep audio by default. In the morning, review the model's time-organized output and available clips. Across multiple nights, compare tagged and untagged nights for associations in your own data.
Step 1 — Before bed, tap what's true tonight
30 seconds of tagging. The first time you do it, it feels like overhead. By night 5 it's a habit, like setting an alarm.
What might be hurting:
🍷 alcohol · ☕ late caffeine · 😰 stress · 🍽️ large meal · 💊 a new medication · 🏃 hard workout
What you're trying:
🛌 side-sleep · 📐 elevated head · 👃 nasal spray · 🪶 anti-snore pillow · 😷 CPAP · 🧘 wind-down routine
Tagging is optional. The app will produce a normal report whether you tag or not. But the Lifestyle Lab™ Factor Impact analysis only works on tagged nights — that's how I know what your variable was that night.
Step 2 — Phone on the nightstand. Plugged in.
Anywhere within arm's reach. 50–90 cm from your head is what I tested in the validation cohort. Microphone facing you. Do Not Disturb on.
Charge it. The app uses about 8–12% battery per night, but the rest of the night your phone keeps running its normal background stuff. Better to wake up with a full battery than a dead one because you forgot to plug in.
One thing worth saying clearly: sleep-audio analysis runs on your phone, and raw audio is not uploaded by default. Your sleep audio is intimate — it can include you, your partner, conversations after bed, or a pet. Audio leaves the device only when you explicitly use Share or Export.
Step 3 — Sleep how you sleep
That's it. There's nothing to wear. Nothing to wake up and check. The app runs as a foreground service with a wake lock; you can lock your phone normally.
One night is a snapshot. A longer run gives more context for your recent personal range. If you tag something specific — a side-sleep belt, an anti-snore pillow, or no alcohol on weeknights — compare several tagged and untagged nights and treat the result as an association, not proof of cause. (Here are common factors people choose to track.)
Step 4 — In the morning, the report is there
You wake up, open the app, and the report is there. The core acoustic analysis runs on your phone, so there is no cloud-analysis delay.
What's in it:
- BRI for the night. A product-defined rate of candidate breathing-irregularity patterns per estimated sleep hour. It is not AHI.
- SRI for the night. Snoring Rate Index — events per hour, plus a Quiet/Light/Moderate/Heavy band. The snoring side. The two indices are independent — you can have a heavy SRI with a normal BRI, or vice versa.
- Q/L/M/H per-minute texture. Four percentages of your night plus a 15-minute color strip across the timeline so you can see when the heavy minutes actually happened, not just how many.
- Candidate events, organized by time. Model-estimated event type, start time, and duration for review.
- Selected audio playback. Free includes 5 plays per night; Pro adds unlimited playback and longer retention. A clip adds acoustic context but does not confirm a medical event.
- Today's tagged factors. What you said before bed gets locked in alongside the report.
Playback is most useful for understanding what the microphone captured around a candidate event. The stronger use case is comparing the overall pattern across multiple nights.
Step 5 — Keep or share a structured summary
Pro summaries organize BRI, SRI, nightly texture, tagged-night comparisons, and longer-term trends in a format that is easier to review outside the app.
Print it, save it, or share it if you choose. It is a wellness-monitoring summary, not a clinical sleep report, and a clinician may still recommend validated medical testing based on your symptoms and history.
See how structured reports complete the longer-term evidence chain →
Why on-device AI (the privacy version, plain)
Your sleep audio is more personal than most people realize. It includes you snoring (private), your partner's breathing (theirs to share, not mine to sell), conversations you had right before falling asleep (no one else's business), and the dog scratching at the door at 2 a.m. (yours).
The AI runs on your phone. Recordings and clips are kept in app-controlled local storage. Audio leaves the device only when you use an explicit sharing or export action provided by the app or operating system.
What we send to our servers: account and subscription data, aggregated sleep statistics, and technical context needed to operate and support the service — never raw sleep audio by default. Full data inventory at /legal/privacy.
What the validation number covers
The published production benchmark reports 88.49% accuracy and 88.06% F1 for labeled 200-second breathing windows. Paper E does not publish a production sensitivity/precision pair, so we do not infer one.
The benchmark does not independently validate every event boundary, duration, product label, phone, bedroom, or personal result. See /accuracy for the claim-by-claim methodology and limitations.
What you do with the data after a few weeks
The value grows as you build a longer personal record:
- First nights — learn what the report contains and inspect a few selected clips.
- Following nights — watch normal night-to-night variation and see your recent range.
- Tagged comparisons — compare nights with and without a factor when enough comparable observations exist.
- Beyond — keep a structured record you can review yourself or share during a professional conversation.
If this is the level of detail that helped, start with Free
A Free plan remains available without a paid subscription: core first-night candidate evidence, 5 audio plays per night, and a recent 7-day trend. An optional 7-day Pro trial adds unlimited playback, longer retention, 30/90-day views, factor comparison, and a fuller structured report. Free audio uses a rolling 7-day local retention window; account deletion and other retention rules are described in the Privacy Policy.
Get the app — free to startPrefer one-time web payment? View Web Pass options →
SomniSense is a wellness tracking tool, not a medical device.