Microsoft adds two Indian languages to its neural text-to-speech service

Microsoft CEO Satya Nadella
Microsoft India announced the addition of English (with Indian dialect) and Hindi to its Neural Text to Speech (Neural TTS) service language set. 

Neural TTS is a part of the Azure Cognitive Services and converts text to lifelike speech for a more natural interface. The service also provides customisable voices, fine-tuned auto control, and flexible deployment from cloud to edge. The two Indian languages are among the 15 new dialects added to the service enabled with artificial intelligence (AI)-driven audio quality.

Neural TTS significantly reduces listening fatigue when users are interacting with AI systems with a natural-sounding speech that matches the stress patterns and intonation of human voices. This makes the service ideal for developing interfaces to communicate with customers. Organizations across sectors like telecom, media, and entertainment, retail, manufacturing, and product/ service development are using Neural TTS. Udaan, India’s largest online business-to-business (B2B) marketplace, is using Text to Speech in Azure to develop conversational interfaces for their voice assistants.


“Our text-to-speech services have played a key role in democratising information reach and empowering people and organisations," Sundar Srinivasan, General Manager, Microsoft India. "Through the inclusion of English (India) and Hindi in Neural TTS, we are demonstrating our continued commitment to refining speech and voice-based services for personal and business use in India. We will continue to drive further advancements in speech services to empower people wherever they are to access information easily.”

Microsoft’s Neural TTS can be used to make interactions with chatbots and virtual assistants more natural and engaging. It is also being used to convert digital texts such as e-books into audiobooks and being deployed for in-car navigation systems. "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," the company's statement said. 

The company also added 13 other new languages such as Arabic (Egypt and Saudi Arabia), Danish, Finnish and Catalan. Overall, Microsoft TTS supports 110 voices and over 45 languages and variants. 



Business Standard is now on Telegram.
For insightful reports and views on business, markets, politics and other issues, subscribe to our official Telegram channel