ADVERTISEMENT
ADVERTISEMENT
Bengaluru-based NYU graduates launch open-source voice AI model
Two 23-year-old Indian founders launch Maya1 that dynamically creates new voices and responds in real time.
-
Pranavi Sharma - Thu, 06, Nov 2025
- 00:11 EST
- 332
Dheemanth Reddy and Bharath Kumar. / LinkedIn
Dheemanth Reddy and Bharath Kumar, both 23 and graduates of New York University, have launched Maya1, an open-source text-to-speech (TTS) model that has quickly become one of the world’s top-ranking voice AI systems. The pair released the model on Nov. 4, 2025, through their Bengaluru-based startup, Maya Research.
According to the Artificial Analysis Speech Arena leaderboard, Maya1 ranks second in the open-weight category and 20th globally among voice AI models, ahead of systems developed by major companies including Google. It supports over 20 emotions, enables zero-shot voice cloning, and operates on a single GPU with latency below 100 milliseconds.
This post is for paying subscribers only
SUBSCRIBE NOW
ADVERTISEMENT
ADVERTISEMENT
E Paper
Video
Comments
Start the conversation
Become a member of New India Abroad to start commenting.
Sign Up Now
Already have an account? Login