Introduction to the Google Assistant ServiceStay organized with collectionsSave and categorize content based on your preferences.
Page Summary
The Google Assistant SDK is for experimental and non-commercial uses only and cannot be used for commercial devices.
The Google Assistant Service provides a streaming endpoint for full control over the Assistant integration.
Basic hardware requirements include a supported device with internet, a microphone, and a speaker.
The guide covers steps for embedding and extending the Google Assistant Service, specifically for Python and Raspberry Pi, with options for other languages and platforms.
The Google Assistant Service gives you full control over the integration with
the Assistant by providing a streaming endpoint. Stream a user audio query to
this endpoint to receive a Google Assistant audio response.
You can generate bindings for this API from a variety of languages (for example,
Go, Node.js, C++, and Java) on all platforms supported bygRPC.
Basic hardware requirements
Before you begin, you'll need the following components:
A device running on one of the supported platforms, with internet
connectivity
A microphone
A speaker
Steps
The following sections are applicable to Python and the Raspberry Pi.
If you do not want to use Python, use theintegration guideto integrate the Google Assistant Service in other languages and on different
platforms.
Embed the Google Assistant
This section gets the Google Assistant Service sample working on your device:
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2024-09-18 UTC."],[],["The Google Assistant Service provides a streaming endpoint for integrating with the Assistant, accepting user audio queries and returning audio responses. It supports multiple languages and platforms. Core actions include setting up hardware (device, microphone, speaker), configuring audio and developer accounts, registering a device model, installing the SDK and sample code, and running the sample. The service can also be extended to handle device actions by installing hardware, registering traits, and handling commands. Commercial use is prohibited.\n"]]
