As artificial intelligence technology advances, the need for naturalness and expressiveness of text-to-speech (TTS) speech is higher than ever. Last month, Microsoft released three new lifelike AI voices designed specifically for conversational scenarios. Recently, Microsoft released 7 new realistic AI voices for more regions in the US East/Southeast Asia/Western Europe regions: French (Canada), French (France), German (Germany), Italian (Italy), Korean (South Korea) , Portuguese (Brazil), Spanish (Spain).
New Lifelike Voice is ideal for any application that requires lifelike voice interaction, including chatbots, voice assistants, games, e-learning, attractions, and more.
In addition to these 7 new voices, Microsoft has also updated 3 current voices with more expressive rhythms. You can find details here.
Here's how Microsoft created these realistic AI voices:
We started by shaping the character of each voice into a real person, friendly and optimistic about life, always eager to Help others and share interesting or useful knowledge. The speaking style of the voice is similar to a conversation over tea with an acquaintance, maintaining a natural and not exaggerated tone.
With this release, Microsoft provides more than 400 neural voices in more than 140 languages and locales. You can check out a demo of these new sounds here.
The above is the detailed content of Microsoft releases 7 new lifelike AI voices optimized for conversations. For more information, please follow other related articles on the PHP Chinese website!