Text-to-Speech (TTS) AI Models for the Sourashtra Language

On October 16, 2026, Digital India Bhashini Division, in collaboration with the Indian Institute of Science (IISc), Bengaluru, announced the development of AI models that convert written text of the Saurashtra language into speech.

Key Facts

Developers: Jointly developed by the Digital India Bhashini Division (under the Ministry of Electronics and Information Technology) and IISc Bengaluru.
Core Technology: Text-to-Speech (TTS) technology converts written words into voice, enabling users to listen to digital content in the Saurashtra language.
AI Models: Based on VITS technology, which generates natural voices from written text. Both male and female voice options are available.
Four Models: A total of four models were developed, covering male and female voices across both Tamil and Saurashtra scripts.
Training Data: IISc's SPIRE Lab prepared over 28 hours of Saurashtra speech recordings to train the AI models.
Sentence Collection: Approximately 10,000 sentences for male voices and 11,400 sentences for female voices were used, including literary material.
AIKosh Platform: The Spikore TTS 3.0 Speech Corpus for Saurashtra is hosted on AIKosh for language technology research.
Saurashtra Language: An Indo-Aryan language primarily spoken by the Saurashtra community in Tamil Nadu. As per the 2011 Census, it had approximately 248,000 speakers.