<p>New Delhi: Agentic AI and Voice Infrastructure firm Gnani.ai, which is building foundational voice models and systems for enterprises and governments, on Wednesday announced the launch of Vachana TTS, a foundational text-to-speech model delivering human-quality speech synthesis with zero-shot voice cloning capability across 12 Indic languages.</p>.<p>Vachana TTS is the second model released under Inya VoiceOS, as part of the India AI Mission. Many AI startups at the India AI Impact Summit demonstrated their new features and products. Gnani.ai is one of four companies selected under the India AI Mission to build sovereign foundational AI models for national-scale deployment.</p>.<p>Vachana TTS supports 12 Indian languages, including Hindi, Bengali, Tamil, Telugu and Kannada, the company said. It enables zero-shot voice cloning using less than 10 seconds of reference speaker audio, it further said, adding that the model is built for low-bandwidth networks and high-concurrency production environments.</p>.<p>Built, trained, and deployed entirely within India, all training data and voice models remain in Indian data centres, ensuring compliance with data localisation requirements, the company said.</p>.<p>Meanwhile, the expo spread across 10 pavilions remained a major attraction on Day 3, witnessing participation from industry leaders, startups, institutions, government representatives, and citizens. A large number of youth and students were seen at the exhibition area.</p>
<p>New Delhi: Agentic AI and Voice Infrastructure firm Gnani.ai, which is building foundational voice models and systems for enterprises and governments, on Wednesday announced the launch of Vachana TTS, a foundational text-to-speech model delivering human-quality speech synthesis with zero-shot voice cloning capability across 12 Indic languages.</p>.<p>Vachana TTS is the second model released under Inya VoiceOS, as part of the India AI Mission. Many AI startups at the India AI Impact Summit demonstrated their new features and products. Gnani.ai is one of four companies selected under the India AI Mission to build sovereign foundational AI models for national-scale deployment.</p>.<p>Vachana TTS supports 12 Indian languages, including Hindi, Bengali, Tamil, Telugu and Kannada, the company said. It enables zero-shot voice cloning using less than 10 seconds of reference speaker audio, it further said, adding that the model is built for low-bandwidth networks and high-concurrency production environments.</p>.<p>Built, trained, and deployed entirely within India, all training data and voice models remain in Indian data centres, ensuring compliance with data localisation requirements, the company said.</p>.<p>Meanwhile, the expo spread across 10 pavilions remained a major attraction on Day 3, witnessing participation from industry leaders, startups, institutions, government representatives, and citizens. A large number of youth and students were seen at the exhibition area.</p>
