Provides user friendly Editor integration and access to Recognition and Synthesis services of Azure Cognitive Services platform which is suited for interactive and game-like scenarios.

For demos please see:

Windows x64 | macOS | Android/ChromeOS | Linux x64

(please be aware that you will need your Subscription Key and Region to be able to run the demo scenes)

- there are several demos - simple speech synthesis and recognition, speech mood customization, automatic ping -pong between speech and recognition (broken telephone game) and echo when syhtesized voice speaks back recognized speech

The asset is built on Microsoft Cognitive Services Speech SDK which is distributed and used according to license terms.

Provides

- Recognition and Synthesis basic tasks

- Synthesis integrates properly with Unity AudioSource / AudioClip

- synthesized audio can be optionally cached locally in WAV format

- Recognition/Synthesis components are scriptable 'the Unity way' and interaction is provided via Unity Events

Up to date documentation

For support please visit forums

Microsoft, Azure and Azure Cognitive Services are trademarks of the Microsoft group of companies.