Getting Started: Sonde Passive SDK

Sonde Health API Platform Documentation

Getting Started: Sonde Passive SDK

 

Sonde’s SDK, as shown below, can be integrated in multiple devices. The SDK provided below is for mobile phone only. For server or embedding SDK in Smart Glasses, Earbuds, Hearing Aids, and Smart Speakers, please contact Sonde.

image-20250626-150436.png

 

Sonde Passive SDK (for Mobile Devices only), product packaging includes:

  • Documentation: Getting Started; Sonde Passive SDK documentation

  • SDK (.aar for Android and .framework for iOS)

  • Sample application source code for both Android and iOS implementation (for integrating the SDK). The SDK and sample application are provided after the execution of an NDA and/or development/production contract with Sonde.

  • Video demo of Passive: https://vimeo.com/1096943789

What is Sonde Passive SDK

The Sonde Passive SDK continuously or periodically monitors your vocal biomarkers based on your voice in real-time. Understanding that these scores do not replace medical evaluations and should be regarded as just one aspect of your overall health and wellness is crucial.

Sonde offers multiple different ways to acquire audio samples:

  • Cued mode - User-facing app asks a paragraph to read or a question. Users' responses is taken as the input voice for scoring.

  • Passive Mode - This mode allows the user-facing app on devices (like phones, smart glasses, or smart speakers) to seamlessly collect audio for scoring while running in the background or foreground. This approach ensures high user adoption as it does not require them to proactively give a daily voice sample.

Developer Demo App Capabilities

This app is designed to help developers with the following key functionalities:

  • Accelerate SDK integration: Refer to the app's source code to quickly understand and integrate the core SDK functionality for ex. Enrollment, User voice analysis, etc.

  • Configure passive mode notifications: Learn how to set up local notifications that prompt users to enable passive mode daily.

Note: Sonde Passive SDK supports both Passive and Cued modes.

Why Integrate Passive

Health changes over time. Vocal biomarkers are ideal for monitoring these changes in Brain and Respiratory health. However, adherence is low when users are asked to give a daily voice sample. Users may go for days or months without give a voice sample, even when the app sends a notification. Three major reasons for integrating Passive mode are:

  • High user adherence - as the user does not need to remember to give a daily audio sample.

  • Higher scoring accuracy - as samples are collected daily and at different times of the day.

  • Strong security and privacy - as no passively collected audio is stored on the device or the Cloud.

SDK Capabilities

Sonde Passive SDK supports the following (when integrated with a Partner’s app):

Audio acquisition

Designed to acquire 16 kHz, 44.1kHz or 48kHz sample audio on the device such as mobile phones, smart speakers.

Audio acquisition

Designed to acquire 16 kHz, 44.1kHz or 48kHz sample audio on the device such as mobile phones, smart speakers.

Voice Activity Detection

The audio acquired is processed and first checked for presence of voice and noise.

User enrollment

Included with the SDK is an enrollment module. A user needs to enroll their voice such that the voice signature template can be used to verify and score only the enrolled user.

User verification

The audio in real-time is verified that it is only enrolled user’s audio. All non-user audio is immediately deleted.

Audio stitching

The system works by analyzing 3-second audio segments every 3 seconds. Each segment is checked against the user's enrolled voice and filtered for quality (SNR). For a segment to be used for scoring, the system requires two consecutive segments to successfully pass these verification criteria.

Scoring

The SDK supports Mental Fitness (MF) and Cognitive Fitness (CF) scoring. MF and CF generates aggregate scores as well as component scores (smoothness, control, liveliness, energy range, clarity, crispness, speech rate, pause duration).

User score history

The SDK does not keep score history. Partner’s app will need to keep this for longitudinal score display and/or trend insights

Microphone Handling

The SDK is designed to automatically regain microphone access after it's lost to other applications, such as phone calls, WhatsApp calls, or Teams calls. The Partner’s App does not need to handle this function.

Real Time

Once 30 sec. of features are collected, the scores are generated in real-time.

Offline

The SDK does not require online/internet connectivity as audio is not shared with backend/cloud.

Privacy

The SDK’s voice analysis module is near 99% accurate in only scoring enrolled user’s voice and deleting it immediately after showing the MF and CF scores.

SDK size

Android: 34.5 MB & iOS: 52.1 MB

Sonde Passive SDK Integration with Partner’s Application

Partner’s application can integrate with Sonde’s SDK. Shown in the block diagram below is the core Passive SDK functions. In lighter shade are modules that Sonde has implemented in its Demo application and offers it as source code. In addition to this, Partners will develop an SDK manager, UI/UX, and score display function and screens (see sample score display screens in Sonde’s Demo App and Mental/Cognitive Fitness App in the App Store). Sonde’s INSIGHT product provides insights (Q4 2025 availability) on scores/trends from Sonde AI Platform.

 

image-20250626-153716.png

 

Sonde Passive SDK Architecture

  • The architecture consists of four major modules:

    • SDK initialization module

    • User enrollment module

    • Voice analysis module

    • Metering module

 

  • SDK initialization module:

    • This module needs to be called at the start with your credentials provided by Sonde Health.

  • User Enrollment module:

    • The Enrollment module must be integrated when a Passive implementation is done. End users will be required to follow these steps:

      Step 1: Find a quiet place

      Step 2: Speak clearly and naturally into your microphone. Articulate each word distinctly to capture the finest nuances of their voice.

      Step 3: The enrollment process involves reading aloud a series of phrases and sentences. This will enable our system to create a comprehensive voice template for the user.

  • Voice analysis module:

    • Voice analysis module works on 30 sec (consisting of 10 3-sec segments) of user verified voice. Once 30 sec voice analyzed app will receive the Mental Fitness and Cognitive Fitness score in call back. Once SDK calculates the score, it purges the 30sec audio data.

    • Score consists of Mental Fitness and Cognitive Fitness scores along with 8 acoustic scores

    • Details regarding each score are described here: Mental Fitness Voice Feature Scores

  • Metering module:

    • SDK includes a metering function to share with Sonde’s backend on the usage of vocal biomarkers. Partners don’t need to handle this integration, this will be an integral part of the SDK.

    • After each session, the SDK shares data with the Metering module.

    • This is critical for billing and quality control.

    • No audio or user’s personal information is included in the metering.

Partner’s UI/UX flow with Sonde Passive SDK

Below are sample screens that may be integrated with Partner’s app. This sample's screen flow is the same as in the sample application source code for Android and iOS implementation (for integrating the SDK).

Please contact Sonde technical support if you would like to try out the Sonde Passive demo.

Sample Wireframes

Screens from the Developer demo app

Best Practices for Sonde SDK Integration in Partner’s App

The following are functions that a Partner may want to add to their application:

User score history

The SDK does not keep score history. Partner’s app will need to keep this for longitudinal score display and/or trend insights

Metering

This is a required function to collect vocal biomarker usage information.

Version

SDK version in the backend linked to the score history

Enrollment

Users should be asked to re-enroll if the user is not being verified. Partners will need to include an option to re-enroll.

Background noise

When passive mode is enabled, users should be in a quiet environment. This can be added to user’s manual.

Distance

The device which is capturing the audio should be less than 3-4 feet from the user and the audio volume should be high

Device battery level

Partner’s app should not enable the Passive mode if the device battery is low

Passive mode enable

Users should be encouraged to keep the Passive mode enabled when they are in a conference call using their computer (on Zoom, Teams, etc.).

Integrations Details

iOS Sonde Passive SDK Integration: iOS Sonde Passive SDK Integration
Android Sonde Passive SDK Integration: Android Sonde Passive SDK Integration

 

Sonde Health