NIGHTTIME BREATHING, OVER TIME

See what happens to your breathing while you sleep — and how it changes over time.

SomniSense shows when breathing patterns changed, lets you review what happened, and helps you compare nights when you tried something different.

From the whole night to the seconds worth reviewing — using only the phone already beside your bed.

No wearable needed · Free basics remain $0 · Pro starts with 7 free days

Then $7.99/mo or $49.99/yr · Web Passes: $19.90/3 months or $89.90 lifetime · See pricing

SomniSense V6 breathing evidence screen showing a selected minute, waveform, highlighted acoustic regions and a whole-night timeline.
Seconds worth reviewing · boxed inside the minute · placed in whole-night context
SomniSense V6 Trends screen showing multiple nights, sample count, BRI and SRI averages, and night-by-night history.
Multi-night baseline
SomniSense V6 Factor comparison explaining tagged and untagged nights, sample sizes and the correlation-not-cause boundary.
Tagged-night comparison

THE FIRST NIGHT

A deeper view of nighttime breathing

Start with the whole night. Then move to the hour, the minute, the waveform and the candidate region worth reviewing. If audio is available, play it back.

SomniSense V6 breathing evidence screen showing a selected minute, waveform, highlighted acoustic regions and a whole-night timeline.
Real iOS V6 screen · selected minute at 6:39 a.m.
  1. 1

    See where the night changed

    The whole-night and hourly views show when detected breathing patterns clustered instead of hiding them inside one nightly number.

  2. 2

    Go back to the minute

    Open the selected minute, inspect its real waveform and see the regions the acoustic model flagged.

  3. 3

    Review the candidate region in context

    See the model-estimated time, duration and pattern label. When audio is still available on the phone, tap play and hear what the microphone captured.

ACROSS NIGHTS

One night is an observation. Several nights become your baseline.

Night-to-night variation is normal. Trends keep the sample count, recording coverage and recent history visible so a single rough night does not become the whole story.

Use the 7-day view first. Longer 30- and 90-day windows are there when enough nights have accumulated to make the comparison worth reading.

See how Trends works →
SomniSense V6 Trends screen showing multiple nights, sample count, BRI and SRI averages, and night-by-night history.
Real iOS V6 Trends view · sample count stays visible
SomniSense V6 Factor comparison explaining tagged and untagged nights, sample sizes and the correlation-not-cause boundary.
Real V6 factor explanation · correlation boundary included

WHEN YOU TRY SOMETHING DIFFERENT

Does the same change keep showing up?

Tag a clear factor before bed — side sleeping, alcohol, an elevated head, a nasal strip or another change you want to observe. SomniSense compares tagged and untagged nights once both groups have enough data.

Correlation, not cause.

The result is an observation, not a verdict. It shows what was associated with higher or lower readings in your nights; it cannot prove what caused the gap.

See how factor comparisons work →

KEEP THE EVIDENCE

A report is the product delivery, not an export afterthought.

SomniSense brings single-night facts, multi-night trends, factor evidence, acoustic patterns, sample coverage, method and limits into one structured wellness report you can save or share.

Open the Reports overview →
Four pages from a real SomniSense V6 structured report showing factor evidence, acoustic patterns, shareable monitoring facts, method and limits.
Real V6 weekly report pages · evidence, method and limits travel together

USE IT WITH WHAT YOU ALREADY HAVE

Already have a score or alert? Add the audio regions behind the night.

A watch or ring can raise the question with its own sensors. SomniSense adds a reviewable acoustic layer — from the whole night, to the minute, to the seconds worth reviewing. Use the phone already beside your bed; neither view replaces PSG, HSAT or professional assessment.

HOW WE VALIDATE IT

Validated in parts, with the limits stated.

Across n=80 paired PSG nights, the published benchmarks report 94.29% accuracy for 1-second snore-segment classification and 88.49% accuracy for 200-second breathing-window classification. Those are different tasks. Neither number turns phone audio into airflow, oxygen, breathing effort, EEG or a diagnosis.

94.29%1-second snore-segment accuracy
88.49%200-second breathing-window accuracy
n=80paired PSG nights · 40 participants

Start your baseline tonight.

The app is available on Google Play and the App Store. The basics are free; Pro adds longer windows, factor comparisons, more retained evidence and structured reports. Choose an app-store subscription or a one-payment Web Pass — the product access is the same.

7-day Pro trial · App stores: $7.99/month or $49.99/year · Web: $19.90/3 months or $89.90 lifetime, no auto-renewal