AVS Device SDK

An easy-to-use SDK for commercial device makers to integrate Alexa into connected products

Simplifying Voice Design

Integrate Alexa directly into your connected product. The AVS Device SDK provides C++-based libraries that enable your device to process audio inputs and triggers, establish persistent connections with AVS, and handle all Alexa interactions. The included capability agents expose the AVS API to handle core Alexa functionality, including speech recognition and synthesis, and other capabilities such as streaming media, timers and alarms, notifications, weather reports, and thousands of custom skills. Additionally, the SDK provides the hooks required to add your own wake word engine and audio player.

Building a Screen-Based Device?

Watch The Tutorial

Key SDK Components

Audio Input Processor

Handles the audio input to Alexa Voice Service from on-device microphones, remote microphones and other audio input sources.

Wake Word Detection (WWD)

Includes the hooks to add your own wake word engine to detect the Alexa wake word in an input stream.

Alexa Communications Library (ACL)

Serves as the main communications channel between the device and the Alexa Voice Service.

Alexa Directive Sequencer Library (ADSL)

Manages the order and sequence of directives from Alexa Voice Service.

Capability Agents

Handles Alexa-driven interactions; specifically, directives and events. Each capability agent corresponds to a specific interface exposed by the AVS API.

Activity Focus Manager Library (AFML)

Prioritizes the channel inputs and outputs as specified by the AVS Interaction Model.

Sign Up for Voice Mail

The Alexa Newsletter for Device Makers