More Realistic & Lifelike Microsoft's Text-to-Speech Voices

Microsoft has revealed its four new voices recently, including zh-CN-YunjieNeural, en-US-EmmaNerual, en-US-AndrewNeural, and en-US-BrianNeural.

The new voices are intended for conversational settings, according to the tech giant, to make user interactions "more realistic, lifelike, and engaging." 

The public may preview the four new voices in three regions: Southeast Asia, West Europe, and the East US. 

Microsoft's new Text-to-Speech voices

In order to clarify the distinction between the new voices suited for discussions and the current voices intended for general use, Microsoft has also provided many demonstrations illustrating the various types of recently integrated voices. 

According to Microsoft, the voices may be integrated into current applications using Azure OpenAI, REST API, Azure Speech SDK, and by utilizing the capabilities of Azure Bot Framework to create intelligent bots that can utilize the new Text-to-Speech (TTS) voices.

Maybe this tendency will be positively impacted by the new voices' emergence. 

It is stated that Microsoft "offers over 400 neural voices covering more than 140 languages and locales," and it appears that the number will increase in the future.

Read more: This $50 Lifetime AI Tool Converts Text to Lifelike Speech