Presentation of ailia AI Voice

ailia AI Voice is a library generating speech from text. It provides a C API for native applications, as well as a C# API well suited for Unity applications. Using ailia AI Voice, you can easily integrate AI powered text-to-speech into your applications.

Features of ailia AI Voice

Multilingual support

You can use English speech synthesis models and Japanese speech synthesis models. For English, you can use GPT-SoVITS or Tacotron2, and for Japanese, you can use GPT-SoVITS.

Running offline

Text-to-speech using ailia Voice does not rely on any cloud service. Moreover, it is possible to run using only a CPU, without any hard requirement for a GPU.

Mobile devices support

In addition to desktop, iOS and Android devices are also supported.

Unity support

In addition to the C API, a C# API and a Unity Plugin are provided, allowing to easily integrate text-to-speech to your apps that are using Unity.

Supported platforms

ailia Voice is available for Windows, macOS, Linux, iOS, and Android.

Voice synthesis in any voice

By using GPT-SoVITS, it is possible to synthesize speech in any voice by providing an audio file of about 10 seconds.