Speech Recognition using Google Cloud [VR\AR\Mobile\Desktop] Pro

Speech Recognition using Google Cloud a true tool for Unity which provides functionality for:

• The recording of voice and the recognition of it

• Setup of Speech Context

• Support of 120 languages and variants

• Fast Speech Recognition

• Offers selection of pre-built models, tailored for your use case

• Automatically transcribes proper nouns and context-specific formatting

• Full included Google Cloud Speech REST API*

• Runtime Voice Detection feature

Based on Google Cloud Speech Recognition

Warning:

• Be sure to read the terms of service of Google Cloud Speech Recognition

• The plugin does not cover the cost of Google Cloud Service

• The plugin does not include Google Cloud Storage API - it means Long Recognize can record only 60 seconds of an AudioClip - Check our Upload/Download using Google Cloud Storage - Pro for recognition of records more than 1 minute

In Pro version - Full source code Included!

Most necessary for communications in VR\AR games and applications!

Forum Thread | Android Demo

Note:

• Works with il2cpp.

• Tested on:

---Android

---IOS

---Windows

---Mac

---Linux

• Works with Unity Cloud Build.

• Doesn't support streaming speech recognition*

• Works in WebGL with integrated Microphone WebGL Library

• Looking for streaming solution? - Check Streaming Speech Recognition

We love to hear from you! Contact us, share your feedback, suggestions at assets@frostweepgames.com

Connect to our Official Discord Server

Release Notes

VERSION 5.0

- V1 API UPDATE. ADDED SUPPORT FOR GC STORAGE ASSET INTEGRATION FOR RECORDS MORE THAN 60 SECONDS. PREPARING FOR V2 API INTRODUCTION (RESTRUCTURED HIERARCHY WITH CODE CHANGES)

VERSION 4.3.1

- FIX FOR NON MOBILE ERRORS

VERSION 4.3

- UPGRADE OF SUPPORT FOR MICROPHONE PRO. UPDATED API. FIXED ERRORS WITH LONG RUNNING API

VERSION 4.2.2

- MEMORY LEAK FIXES OF NETWORK

VERSION 4.2.1

- IMPROVEMENTS OF MICROPHONE CORE USAGE

VERSION 4.2

- CORE UPDATE. OPTIMIZATIONS. API UPDATE

Version 4.1.2

~ updated API of Google Service

Version 4.1.1

~ general fixes

Version 4.1

- core improvements

- fixes and polishing

- added compatibility for webgl support

- updated api

Version 4.0.1

- updated example

- added few help api

Version 4.0

- updated networking

- improved core

- fixed bugs

- implemented new features

- updated examples list

- added api for android permissions

- price changes

Version 3.2.1

- edited description

Version 3.2

~ implemented word-specific information for recognized words

~ added support of 'checking key signature of the android certificate'

~ improved code

~ fixed bugs

Version 3.1

~ Implemented Full Long Recognize Api

~ Implemented All languages that the Google Speech Recognition supporting

~ Fixed bugs

~ Added Newtonsoft.Json Serializer\Deserializer

~ Improvements in general

Version 3.0:

~ Updated API to the latest 1.0 version

~ New code architecture (SOA)

~ Added async networking (Unity Web Requests)

~ Removed support of WebGL (will be added in future updates)

~ Not Fully implemented Long Recognize API

~ Improved Examples

~ Improved Config Prefab

~ Improved runtime voice detection service

~ Improved media service

~ Improved audio converter

~ Added audio tools

Version 2.3:

~ fixed small bugs

Version 2.2.1:

~ introduced webgl template for correct working of microphone

Version 2.2:

~ implemented new features

~ fixed bugs

~ more improvements

~ implemented support of WebGL(Experimental)