Gnani.ai launches zero-shot voice cloning TTS model for 12 Indic languages
Gnani.ai's Vachana TTS brings multilingual voice cloning to Indian languages with human-like speech output.
- Feb 19, 2026,
- Updated Feb 19, 2026 12:15 PM IST
Homegrown artificial intelligence (AI) startup Gnani.ai launched a text-to-speech model capable of zero-shot voice cloning across multiple Indian languages, as the country pushes to build domestic AI capabilities under the India AI Mission.
The model, called Vachana TTS, delivers human-quality speech synthesis in 12 Indic languages and can replicate a speaker’s voice using less than 10 seconds of audio, the company said.
Gnani.ai said the system supports languages including Hindi, Bangla, Tamil, Telugu, Kannada, Malayalam, Gujarati, Marathi, Punjabi, Odia, Assamese and Indian English, enabling organisations to maintain a consistent voice identity across regions.
The company, one of four selected under the India AI Mission to build sovereign foundational models, said the technology is designed for large-scale deployment across government services and businesses.
"Voice synthesis is not about converting text to audio. It is about preserving the human qualities that make communication effective," Ganesh Gopalan, co-founder and chief executive of Gnani.ai, said.
"With Vachana TTS, we are bringing genuine emotion into synthesized speech, warmth, urgency, empathy, delivered with significantly better accuracy than anything built for Indian languages before, and at a price point that makes it accessible to every enterprise and government body in the country," he said.
The model enables cross-lingual voice cloning, allowing the same voice to speak multiple languages while preserving characteristics such as pitch, speech rate and speaking style, the company said.
Gnani.ai said Vachana TTS is built for low-bandwidth environments and high-volume usage, supporting both real-time streaming for conversational systems and batch processing for large-scale content generation.
According to the company, potential applications include public announcements, educational content, emergency alerts, call-centre systems and conversational AI agents, particularly for populations with low literacy or visual impairments.
Vachana TTS is available immediately via API access, with on-premises deployment options for regulated sectors, the company added.
For Unparalleled coverage of India's Businesses and Economy – Subscribe to Business Today Magazine
Homegrown artificial intelligence (AI) startup Gnani.ai launched a text-to-speech model capable of zero-shot voice cloning across multiple Indian languages, as the country pushes to build domestic AI capabilities under the India AI Mission.
The model, called Vachana TTS, delivers human-quality speech synthesis in 12 Indic languages and can replicate a speaker’s voice using less than 10 seconds of audio, the company said.
Gnani.ai said the system supports languages including Hindi, Bangla, Tamil, Telugu, Kannada, Malayalam, Gujarati, Marathi, Punjabi, Odia, Assamese and Indian English, enabling organisations to maintain a consistent voice identity across regions.
The company, one of four selected under the India AI Mission to build sovereign foundational models, said the technology is designed for large-scale deployment across government services and businesses.
"Voice synthesis is not about converting text to audio. It is about preserving the human qualities that make communication effective," Ganesh Gopalan, co-founder and chief executive of Gnani.ai, said.
"With Vachana TTS, we are bringing genuine emotion into synthesized speech, warmth, urgency, empathy, delivered with significantly better accuracy than anything built for Indian languages before, and at a price point that makes it accessible to every enterprise and government body in the country," he said.
The model enables cross-lingual voice cloning, allowing the same voice to speak multiple languages while preserving characteristics such as pitch, speech rate and speaking style, the company said.
Gnani.ai said Vachana TTS is built for low-bandwidth environments and high-volume usage, supporting both real-time streaming for conversational systems and batch processing for large-scale content generation.
According to the company, potential applications include public announcements, educational content, emergency alerts, call-centre systems and conversational AI agents, particularly for populations with low literacy or visual impairments.
Vachana TTS is available immediately via API access, with on-premises deployment options for regulated sectors, the company added.
For Unparalleled coverage of India's Businesses and Economy – Subscribe to Business Today Magazine