Francisca, our new Brazilian Portuguese (pt-BR) voice, has been added to neural Text to Speech. Francisca features the same human-like natural prosody of the other neural Text to Speech voices on Azure. Francisca can generate realistic speech waveforms for a given text input, matching the patterns of stress and intonation transitions in spoken language seamlessly.
In addition to the capability to synthesize speech, developers can also tailor the voice for different scenarios with different voice styles using neural Text to Speech. For example, the new pt-BR voice can also speak with a “cheerful” tone, which can be used to express an emotion that’s positive and happy. This is particularly useful in chat bot scenarios. Adjust the speaking styles easily with the <mstts:express-as> element in speech synthesis markup language.
Learn more.