Microsoft’s Azure AI Text to Speech service allows you to convert text into speech in different languages. Early this year, Azure AI Text to Speech introduced the JennyMultilingual voice that allowed customers to generate speech in a consistent persona across locales. Until now, the JennyMultilingual voice supported 14 languages. Today, Microsoft announced the expansion of the multilingual voice capability to 41 languages and accents.
Today, Microsoft also announced a new male voice (RyanMultilingual) as part of its multilingual portfolio. These new voices come with the auto language prediction capability for the input text. So, this eliminates the need for manual tagging as the voice can automatically recognize the input languages and adjust the speech output accordingly. Also, this system can dynamically adapt its pronunciation, intonation, and phonetics to match the specific linguistic nuances of different languages.
These new Azure AI Text to Speech updates will be in public preview in the following three regions: East US, West Europe, and Southeast Asia.