Pioneering Text-to-Speech Model supporting 22 Indic Languages alongside English

EDUCATION

Gan.AI Launches Myna-mini: Pioneering Text-to-Speech Model supporting 22 Indic Languages alongside English a leading startup in conversational AI research and products, today announced the launch of Myna-mini, a groundbreaking text-to-speech (TTS) model and API. This research preview marks a significant milestone in language technology, being the first and only TTS model in the world to support all 22 Official Indic languages alongside English.

Key Features x Myna-mini:

  • Support for 22 Indic Languages and English: Comprehensive linguistic coverage.
  • Multiple Distinct Voices: Reflecting the diverse regions of India.
  • Native Code-Mixed Language Support: Seamlessly handles multilingual inputs.
  • High-Quality, Natural-Sounding Voice Output: Superior voice fidelity.
  • User-Friendly API: Easy integration for developers.
  • Free Access via Gan.AI Playground : Try out the technology at no cost.

Code-mixed support means Myna-mini can seamlessly handle text that mixes multiple languages in a single sentence or paragraph. This reflects how people naturally communicate, switching between languages mid-conversation. Myna-mini is the result of extensive research and development by Gan.AI Launches Myna-mini: Pioneering Text-to-Speech Model supporting 22 Indic Languages alongside English’s team, which includes experts from prestigious institutions and tech giants such as Stanford, FAIR, IITs, BITS, Samsung, Microsoft, and Adobe Research. The team boasts over 1000 combined research citations in the field.

“Myna-mini represents a significant step towards making AI accessible and useful for everyone, regardless of the language they speak,” said Suvrat, founder and CEO of Gan.AI. “We’re excited to bridge the language gap and bring advanced voice technology to over 1 billion people.”

The launch of Myna-mini is just the beginning Gan.AI has announced plans for even more advanced models, including:

  • Myna and Myna-Large: Set to be the world’s largest TTS models in terms of training data and parameter count
  • Zero-shot cross-lingual voice cloning
  • Lip-sync API
  • Avatar API

Gan.AI s technology has already been trusted by world-renowned brands for personalizing video and audio campaigns, including Uber, Cadbury, Swiggy, Zomato, the San Antonio Spurs, and Mumbai Indians.

Developers, researchers, and businesses are invited to explore Myna-mini at playground.gan.ai. Gan.AI welcomes feedback from the community to guide future development and improvements.