Stillpoint: a two-minute breathing retreat that learns your rhythm

This is a submission for the Presage SmartSpectra SDK Challenge

TL;DR: A two-minute, camera-only breathing retreat that learns your rhythm with the Presage SmartSpectra SDK, then paces you from it. Local-only, no score, no wearable.

What I Built

Stillpoint is a two-minute, camera-only breathing retreat. It measures your natural breathing
rate through a webcam, then guides you into a slower rhythm that starts from where you already are.

Most breathing apps ask you to match a fixed pace. Stillpoint does the opposite: it spends 32
seconds quietly learning your rhythm, then eases the guide toward a calmer 10-second breath without
ever making a slow breather go faster. An orb grows and settles with the pace, live pulse and
breathing values appear as they become reliable, and the landscape subtly responds to your
expression if you enable that optional setting.

There is no wearable, no account, no recording, and no upload. The whole experience is designed
around a simple constraint: the camera frames should never leave the machine.

Demo

Watch the 2-minute demo (MP4)

Release page: https://github.com/pham-canh/stillpoint/releases/tag/demo-v1

The demo shows a live session on a Linux x64 machine with a USB camera: the local camera preview,
live SmartSpectra pulse and breathing readings (HRV when the signal is ready), validation hints, the
adaptive pacer, and the summary. The app is shown running locally, which is the intended deployment.
The recording uses a 70-second shortened session via SETTLE_MS / SESSION_MS; the default is 32
seconds of settling plus 90 seconds of guided breathing.

Code

https://github.com/pham-canh/stillpoint

Setup:

git clone https://github.com/pham-canh/stillpoint.git
cd stillpoint
npm install
cp .env.example .env   # add SMARTSPECTRA_API_KEY
npm start
# open http://127.0.0.1:4317

Requirements and platform notes are in the README. The SmartSpectra Node SDK ships native
binaries, so the app runs on macOS Apple Silicon, Linux x64/arm64, and Windows x64; Intel Macs are
not supported by the SDK. The UI still loads on unsupported platforms, and a local video can drive
the same pipeline through DEMO_VIDEO for testing.

How It Responds to Human Signals

Stillpoint uses three live SmartSpectra signals by default — pulse rate, breathing rate, and
HRV — plus expression when the optional scene setting is enabled. It requests only those
four metrics, not traces, landmarks, blinking, or talking.

The integration path:

1. The local Node process opens the camera with the SDK's native useCamera(CameraSelection.byId(id), { width: 1280, height: 720, fps: 30 }) path. Frames stay inside that process; there is no browser-to-server frame hop and no browser camera prompt in the default mode.
2. The SDK emits metric buffers. decodeMetrics reads metrics.breathing.rate.at(-1), metrics.cardio.pulseRate.at(-1), metrics.cardio.hrv.at(-1), and, when enabled, metrics.face.expression.at(-1).
3. The SDK's videoOutput event provides a processed frame. The server downsamples it to a 320×240 RGBA preview and sends it to the browser over the loopback control WebSocket, so the person can check framing without a second camera consumer.
4. The server pushes deduplicated samples to the browser over Server-Sent Events. The optional CAPTURE_MODE=frames fallback keeps the original browser getUserMedia → 640×480 RGBA → useCustomInput() / sendFrame() path for machines where the server cannot access a camera.

How the experience reacts:

• Breathing rate becomes the starting pace. After a 32-second settle, the pacer begins at the measured period, clamped to 6–12 seconds. It eases toward 10 seconds by 750 ms per breath. If your measured rhythm is slower than 10 seconds, it stays there.
• The orb is the guide. Inhale takes 40% of the cycle and exhale 60%. The orb's radius, the landscape's mist, and the reflection on the lake all follow the same breath value.
• Pulse drives subtle ripples. Reliable pulse samples add heartbeat ripples to the lake, so the scene feels connected to the measurement without turning the session into a dashboard.
• HRV is shown, not scored. RMSSD appears when confidence is high enough; there is no gamification.
• Expression is optional art direction. If enabled, the strongest expression label blends the scene palette. Turning it off removes the expression metric from the SDK request entirely.
• Validation hints are actionable. "Face not centered", "too dark", "chest not visible", and similar SDK hints appear on the preview, then fade back to the resting instruction.

The app uses live SDK readings in the default camera mode. The DEMO_VIDEO option uses the same
pipeline with useFile() and is intended for tests and recordings, not as the primary experience.

Prize Categories

Entering both:

• Most Creative or Delightful Use — a webcam becomes a quiet, responsive landscape rather than a vitals dashboard. The adaptive pacer starts from the person instead of a preset, and the optional expression palette makes the same two minutes look different for different people.
• Best Thoughtful Real-World Use — a low-friction two-minute microbreak for desk workers, students, and caregivers. No wearable, no account, no streak, no score. The session is short enough to repeat, and the privacy design removes the main reason people avoid camera-based tools.

Consent and Data Handling

Consent. The camera is not opened until the person ticks an explicit consent checkbox and
presses Begin. In the default native mode the local Stillpoint process opens the camera at that
point; the browser does not request camera access, so there is no extra browser prompt. Expression
analysis is optional and off by default; it can be enabled before starting.

Frames. Video only, never audio. In the default mode the local Node process opens the camera at
up to 1280×720 and the SDK processes frames in memory. A downsampled 320×240 RGBA preview is sent to
the page over a loopback WebSocket. Frames are not recorded, written to disk, cached, logged, or
uploaded. The live preview is local and can be hidden. The CAPTURE_MODE=frames fallback uses
browser capture and a loopback frame WebSocket instead.

Measurements. Pulse, breathing, HRV, and optional expression are computed locally by the
SmartSpectra SDK running natively in the Node process. Derived values are held in memory for the
session, shown in the interface, and discarded when the session ends. Stillpoint does not persist
them.

Network and third parties. Stillpoint does not send frames or measurements to Presage. The
SmartSpectra SDK authenticates the API key, verifies the subscription, and may obtain its model or
update files from Presage; those requests do not include Stillpoint's frames or measurements.
Stillpoint has no accounts, analytics, ads, or tracking, and uses no optional AI service. The SDK
telemetry option is explicitly disabled (enableTelemetry: false). The page loads no external
scripts, fonts, or images.

Retention and deletion. There is no stored data to retain or delete. Stopping the session,
pressing Escape, hiding the tab, disconnecting, or finishing normally releases the camera, closes the
sockets, and releases the in-memory session state. Closing the tab clears the rest.

Security. The server binds to 127.0.0.1, origin-checks WebSocket and control requests, and sets
a strict Content Security Policy. The intended URL is http://127.0.0.1:4317.

Demo video. The recording was made separately, with the participant's consent, outside the app's
data path. Stillpoint itself does not record the session. If the optional DEMO_VIDEO setting is
used, it reads a local clip chosen by the operator; that clip is not uploaded.

Full details: https://github.com/pham-canh/stillpoint/blob/main/PRIVACY.md and the in-app /privacy page.

Wellness only. SmartSpectra metrics are not FDA-cleared and are not a diagnosis or treatment.
Stillpoint does not provide medical advice, make medical decisions, or monitor anyone covertly.

Comments

[OneLifeVibe]

The decision to start from the person's actual breathing rate, rather than a fixed pace, is what makes this stand out. Most breathing apps ask the body to meet the app; here the app meets the body first, and that 32-second settle feels like the honest way to do it. Showing HRV without turning it into a score is a thoughtful touch too — it keeps the two minutes calm instead of competitive. The local-only camera handling is reassuring as well. Curious how the adaptive pacer behaves for someone whose natural rate is already very slow — does it still try to ease toward ten seconds, or does it mostly hold steady?

[Phạm Cảnh]

Thanks — it holds steady. The pacer starts at the measured period (clamped to 6–12s) and only eases toward 10s when the measured period is shorter than 10s. If someone's natural period is 10–12s, the target is their own period, so the guide doesn't shorten it; it just stays with them. The one edge case is the 12s cap: a natural breath longer than 12s stays at 12s rather than going slower, so the guide remains usable. The pacer tests cover both cases.