The VitalLens API is a web-based service that estimates a person's vital signs from a video of their face and upper body.

VitalLens API uses remote photoplethysmography (rPPG): it tracks tiny, frame-by-frame skin-color shifts in your face video to rebuild the PPG waveform, then derives heart-rate, HRV, and respiratory-rate.

For a deeper technical dive, see our explainer article: Understanding Remote Photoplethysmography .

TLDR: Heart rate (HR), Heart rate variability (HRV), respiratory rate (RR), pulse waveform, and respiratory waveform.

The API provides an estimate of the pulse and respiratory waveforms at the same sampling rate as the video. From these, HR, HRV, and RR are derived.
We currently support SDNN, RMSSD, and LF/HF metrics for HRV. Future releases may include additional vital signs such as blood oxygen (SpO2) and blood pressure (BP).

TLDR: Estimates are highly accurate for high-quality video. Each estimate includes an estimation confidence.

We conducted a study on a large, diverse test benchmark including 422 unique individuals (including data from Vital Videos, UBFC-rPPG, and UBFC-Phys) showing a mean absolute error for HR at 1.57 bpm, for RR at 1.08 bpm, and for HRV-SDNN at 10.18 ms.
Lower confidences indicate less accuracy, which can be improved with high-quality videos.

To get access to the VitalLens API, please use the button above to register for an API Key. After you sign up and confirm your email address, we will automatically generate your unique API Key associated with the free plan. You can then log in on this page to view your API Key and start using the VitalLens API.

For each request, the VitalLens API accepts a maximum of 900 frames of spatially downsampled video depicting a single person's face and upper body at resolution 40x40px. This video is passed through our estimation engine, which produces estimates for several vital signs. These estimates are then sent back, after which both the video frames and estimates are disposed of.

Please consult our API Documentation to learn how to use the VitalLens API.

Yes, the VitalLens API is versatile and supports both use cases:

- Real-time Analysis: Use our JavaScript client (or the /stream endpoint) to estimate vitals live from a webcam feed or video stream.
- Ex-post Analysis: Use our Python client (or the /file endpoint) to analyze pre-recorded video files uploaded for processing.

Regardless of the method, usage is always calculated based on the total number of frames processed.

The returned object for a request to the VitalLens API looks like this:

{
  'vital_signs': {
    'heart_rate': {
        'value': Estimated value as float scalar,
        'unit': Value unit,
        'confidence': Estimation confidence as float scalar,
        'note': Explanatory note
      },
    'respiratory_rate': {
      'value': Estimated value as float scalar,
      'unit': Value unit,
      'confidence': Estimation confidence as float scalar,
      'note': Explanatory note
    },
    'hrv_sdnn': {
      'value': Estimated value as float scalar,
      'unit': Value unit,
      'confidence': Estimation confidence as float scalar,
      'note': Explanatory note
    },
    'hrv_rmssd': {
      'value': Estimated value as float scalar,
      'unit': Value unit,
      'confidence': Estimation confidence as float scalar,
      'note': Explanatory note
    },
    'hrv_lfhf': {
      'value': Estimated value as float scalar,
      'unit': Value unit,
      'confidence': Estimation confidence as float scalar,
      'note': Explanatory note
    },
    'ppg_waveform': {
      'data': Estimated waveform value for each frame,
      'unit': Data unit,
      'confidence': Estimation confidence for each frame,
      'note': Explanatory note
    },
    'respiratory_waveform': {
      'data': Estimated waveform value for each frame,
      'unit': Data unit,
      'confidence': Estimation confidence for each frame,
      'note': Explanatory note
    },
  },
  'face': {
    'confidence': Face live confidence for each frame,
    'note': Explanatory note
  },
  'message': Message about estimates
}

Our Python Client, JavaScript Client, and SDKs are provided to handle face detection, video cropping and spatial downsampling, splitting of longer videos, as well as API interaction for you.

- Minimize camera movement.
- Keep the subject still and facing the camera.
- Ensure a bright and steady light source.
- Use as little video compression as possible if you need to encode the video before using the VitalLens API. Video compression can destroy the vitals signal.

Your plan provides a set number of frame credits. The duration of video analysis this covers depends on the frame rate (fps) you choose to use. For example:

- Offline Analysis (Standard): Typically uses 30 fps for maximum precision. Analyzing 1 minute of video costs 1,800 frame credits (60s x 30 fps).
- Real-time Analysis (Eco Mode): Often uses 15 fps to save bandwidth. Streaming for 1 minute costs 900 frame credits (60s x 15 fps).

Please note that these are just examples. You can configure either real-time or offline analysis to run at 30 fps or 15 fps depending on your specific accuracy requirements and budget.

While our API plans are strictly billed by frame credits (the total number of video frames analyzed), we use "Scans" to help you estimate plan capacity.

We define a standard Scan as 1,000 frames. This allocates credits for a standard 30-second measurement at 30 fps (900 frames), plus a 100-frame buffer to account for potential restarts or setup overhead.

Calculation: (30 seconds × 30 fps) + 100 buffer frames = 1,000 frames per Scan.

Actual usage varies based on your settings. For example, using Eco Mode (15 fps) halves the number of frames per scan, effectively doubling the number of scans provided by your plan.

"Eco Mode" refers to configuring your client to analyze video at 15 frames per second (fps) rather than the standard 30 fps.

Because the VitalLens API bills by the frame, halving the frame rate consumes half the credits per second of video. This effectively doubles the number of scans available in your plan while maintaining sufficient accuracy for most heart rate and respiratory rate use cases.

Please visit our plan picker to identify and purchase the plan that suits your needs.

No, we do not collect or store any of your video or vital sign estimates data. After returning the API request result, we immediately dispose of this data - hence it is your responsibility to store the returned estimates. Please also see our Terms of Service for more information.

No, VitalLens is not a medical device and its estimates are not intended for any medical purposes. Please also see our Terms of Service for more information.