Microsoft’s Neural Text to Speech now supports English India, Hindi

Microsoft on Tuesday announced the addition of English (India) and Hindi to its Neural Text to Speech (Neural TTS) service language set. The Neural TTS is part of Microsoft’s Azure Cognitive Services and aims at delivering lifelike speech conversion from the text along with a more natural interface. Azure’s suite also brings additional features such as customisable voices, fine-tuned auto control, and flexibility to deploy the TTS from cloud to edge.

Microsoft claims that its Neural TTS reduces listening fatigue by matching natural-sounding speech which is further based on analysing stress patterns and intonation of human voices. The platform could further help businesses integrate the service for customer support. Industries such as telecom, media, entertainment, retail, and manufacturing can employ the feature. Microsoft pointed out that Udaan, a popular B2B marketplace, is already using the company’s Text to Speech in Azure to develop conversational interfaces for their voice assistants.

ALSO READ: When Bill Gates called Steve Jobs a genius and said he was jealous of him

The company is optimistic that its Neural TTS can be further used for improving interactions with chatbots and virtual assistants. Other use cases include converting digital texts in e-books into audiobooks. The platform can also be used for an in-car navigation system.

ALSO READ: IBM, NSDC join hands to offer free digital skills training

“The service enables human-like natural and clear articulation and uses deep neural networks to overcome the limits of traditional text-to-speech systems in matching the patterns of stress and pitch in spoken language. Neural TTS offers these benefits while maintaining comprehensive privacy and enterprise-grade security through data encryption,” the company further said in a post.

The new English (India) and Hindi are among the 15 new dialects added to the service. Other new languages introduced are Arabic (Egypt and Saudi Arabia), Danish, Finnish, Catalan, Polish, Dutch, Portuguese, Russian, Thai, Swedish, and Chinese (Cantonese Traditional and Taiwanese Mandarin). Overall, the platform supports 110 voices and over 45 languages and variants.