Google DeepMind Launches Project Vaani 2: Multimodal Datasets for 50+ Indian Dialects
Collaborating with the Indian Institute of Science (IISc), Google DeepMind releases 14,000 hours of open-source conversational audio across 80 Indian districts.
Bridging the Vernacular Audio Divide
Project Vaani Phase 2 expands the largest open-access Indian speech repository in history, capturing authentic dialects across rural Maharashtra, Uttar Pradesh, and Bihar.
Empowering Vernacular Voice Agents
The open-source audio corpus is freely accessible for Indian researchers building agricultural advisories, fintech voice bots, and healthcare assistants tailored to non-English speaking citizens.
Written by AI Latest News Editorial Team
Dedicated team of AI researchers, benchmark evaluators, and technology journalists in Bengaluru, Hyderabad, and Delhi.
View all articles by AI Latest News Editorial Team →Discussion (0)
No comments yet. Start the conversation!
Recommended Reading
DeepSeek-R1 Disrupts Global AI Economics: Silicon Valley and Indian Startups React
DeepSeek's release of open-weights reasoning model R1 has sent shockwaves across global tech markets, offering o1-level chain-of-thought at 95% lower API cost.
ChatGPT vs Claude vs Gemini: Which Is Best in India in 2026?
We stress-tested OpenAI ChatGPT Plus, Anthropic Claude 3.5 Sonnet, and Google Gemini 1.5 Pro across Indian English, regional language reasoning, UPI coding tasks, and rupee pricing.
Sarvam AI Unveils Sarvam-1: India's 2B Parameter Model Outperforming Llama on Indic Tasks
Trained on 4 trillion tokens across 10 Indian languages, Sarvam-1 demonstrates state-of-the-art tokenization efficiency and vernacular comprehension.