Azure AI's text-to-speech feature already supports 41 multilingual voices

Microsoft’s Azure AI text-to-speech service allows you to convert text into speech in different languages. Earlier this year, Azure AI Text-to-Speech introduced JennyMultilingual Speech, allowing customers to generate speech with consistent personas across locales. So far, Jenny multilingual voice supports 14 languages. Today, Microsoft announced the expansion of multilingual speech capabilities to 41 languages ​​and accents.

Today, Microsoft also announced a new male voice (Ryan Multilingual) as part of its multilingual product portfolio. These new voices feature automatic language prediction for input text. This therefore eliminates the need for manual tagging as the speech automatically recognizes the input language and adjusts the speech output accordingly. Additionally, the system can dynamically adjust its pronunciation, intonation and voice to match the specific linguistic nuances of different languages.

These new Azure AI text-to-speech updates will be available in public preview in three regions: US East, Western Europe, and Southeast Asia.

The above is the detailed content of Azure AI's text-to-speech feature already supports 41 multilingual voices. For more information, please follow other related articles on the PHP Chinese website!