Microsoft introduces Hindi, Indian English to Neural Text-to- Speech service1 min read . Updated: 25 Aug 2020, 01:19 PM IST
- 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 customizable voices, fine-tuned auto control, and flexible deployment from cloud to edge
Microsoft India has announced the addition of English (India) and Hindi to its Neural Text to Speech (Neural TTS) service language set, featuring the two languages among the 15 new dialects added to the service enabled with state-of-the-art artificial intelligence (AI) audio quality.
This addition will help far more users in India, especially in the non-metro areas, to use this feature and will thus expand Microsoft's reach in such regions.
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 customizable voices, fine-tuned auto control, and flexible deployment from cloud to edge, it said.
"Our text-to-speech services have played a key role in democratizing information reach and empowering people and organizations. 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," said Sundar Srinivasan, General Manager, Microsoft India (R&D) Pvt Ltd.
With natural-sounding speech that matches the stress patterns and intonation of human voices, Neural TTS significantly reduces listening fatigue when users are interacting with AI systems. It makes the service ideal for developing interfaces to communicate with the customers, Microsoft said. The addition of the two languages will thus also help businesses expand in non-metro regions.
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 audio books 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.
Neural TTS offers these benefits while maintaining comprehensive privacy and enterprise-grade security through data encryption. The 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, Microsoft TTS supports 110 voices and over 45 languages and variants, the IT firm said.