Skip to content

Here is everything you need to know about the Snips Voice Platform

Notifications You must be signed in to change notification settings

clonemvp/snips-platform-documentation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

28 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Snips Voice Platform Documentation

Snips Voice Platform

About the Platform

The Snips Voice Platform allows anyone to integrate AI powered voice interaction in their devices with ease. The end-to-end pipeline - Hotword detection, Automatic Speech Recognition (ASR) and Natural Language Understanding (NLU) - runs fully on device, powered by state of the art deep learning. By using Snips, you can avoid cloud provider costs, cloud latency, and protect user's privacy.

Your voice assistant in English, French, German, Spanish or Korean (more to come) can be configured easily via a web console. You can select pre-built assistants, or create completely custom ones. Today, the assistant can be deployed to a Raspberry Pi 3. More platforms are available for enterprise clients, contact us at contact@snips.ai.

Getting Started

You will find everything you need in the wiki. You can get started with the overview, or alternatively, navigate the doc from here:

  1. Overview

  2. Setup the Snips Voice Platform on your Raspberry Pi

  3. Running your first end to end assistant

  4. Building an end to end assistant with a custom intent

  5. Create an assistant with custom slot types (advanced)

  6. Learn more: Key Concepts

  7. Learn more: Platform Commands

  8. Learn more: built in resources

  9. Learn more : Snips Internals

Contact us

FAQ

About this repository code

You'll also find here sample code for handlers both in python and node. We strongly advise to get started with the wiki, that will route you to these samples at the right time.

About

Here is everything you need to know about the Snips Voice Platform

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published