This package provides a user-friendly interface for integrating Speech-to-text and Text-to-speech services from Azure Cognitive Services into your Unity project. It's ideal for interactive and game-like scenarios. The package includes demos for speech synthesis and recognition, mood customization, and more. It's built on the Microsoft Cognitive Services Speech SDK and is compatible with Windows, macOS, Android, and Linux platforms. The package provides basic recognition and synthesis tasks, integrates with Unity's AudioSource and AudioClip, and allows for local caching of synthesized audio in WAV format. The components are scriptable and interact via Unity Events.
The package is built on the Microsoft Cognitive Services Speech SDK and is distributed according to the terms of the SDK's license. The package is up to date with the latest documentation and support is available through the provided forums.
