Microsoft has launched four text-to-voice TTS for AI chat scenarios, which are more natural and personified.

CTOnews.com Sept. 22, Microsoft said that with the popularity of generative AI around the world, users also put forward higher requirements for the naturalness and expressiveness of text-to-voice in the process of chatting with AI.

Microsoft today announced the release of four TTS voice models, en-US-AndrewNeural, en-US-BrianNeural, en-US-EmmaNerual and zh-CN-YunjieNeural, which are currently available in public previews in the eastern United States, Southeast Asia and Western Europe.

Microsoft officials say the four TTS voices can provide natural voice interaction, making the chat voice more realistic, more natural, and more attractive.

In the press release, Microsoft also showed the comparison of four TTS voices and demonstrated different tone styles. CTOnews.com attached a link so that interested users can click deeply.

Microsoft says developers use Azure Speech SDK,REST API to integrate voice into existing applications through Azure OpenAI.