DIFF-2 · SEE & HEAR PLAYBACK
You're not reading numbers. You're listening to your night.
Charts summarize a night. Playback lets you inspect selected local clips behind candidate acoustic events. It adds context to the model output without turning it into a diagnosis.
Free includes candidate-event evidence, 5 audio plays per night, and a 7-day trend. Pro adds evidence continuity.
Charts summarize a night. Local playback lets you inspect selected clips behind the model's candidate events. The AI runs on your phone, and sleep audio stays there by default unless you explicitly choose to share a clip.
Review the recording behind a data point
A chart can show where the model found an unusual acoustic pattern. Playback gives you additional context: what the microphone actually captured at that time.
A clip may contain snoring, a quiet interval, movement, a partner, room noise, or another sound. Listening can help you understand the report, but it does not turn an acoustic label into a clinical finding.
What you may hear
For candidate events with an available clip, playback lets you hear the corresponding part of your locally stored recording.
- Snore-like sounds identified by the model
- Quiet or reduced-breathing-like intervals marked for review
- Other room sounds that may explain or add context to a candidate event
Phone audio alone cannot establish airway anatomy, airflow reduction, oxygen level, arousal, or a medical condition. Use clips as supporting context within your multi-night wellness record.
Why on-device — and what that means for your audio
Your sleep audio is more intimate than most people realize. It contains things your conscious memory doesn't. It contains your partner. It contains conversations you had after going to bed. It contains the dog scratching at the door at 2 a.m.
So here's exactly what happens with it:
- The AI runs on your phone. Audio doesn't get sent anywhere by default.
- Recordings and clips are kept in app-controlled local storage. You can delete sessions from the app.
- Audio leaves the device only when you use an explicit sharing or export action provided by the app or operating system.
I designed it this way because if I were the user, I would not put my own sleep audio in someone else's cloud. That's the actual reason — not a privacy badge for marketing.
Free vs Pro on this feature
Free: 5 audio plays per night. Enough to inspect selected clips behind the first-night evidence.
Pro: Unlimited playback with longer evidence retention. Pro pays for continuity; the core candidate evidence remains available in Free.
Playback limits apply to in-app access. Your audio is processed on device and is not uploaded to SomniSense by default.
Free keeps core first-night evidence and 5 audio plays per night. Pro adds unlimited playback and longer continuity.
Read next
- → Lifestyle Lab™ — the data that comes after you trust the audio
- → Why your sleep audio never leaves your phone — the privacy architecture in plain language
- → Every-Event Timeline — when the events happen, not just how many
- → Privacy policy — the full details of how audio is handled