New Delhi, Sept 7 (PTI) Blue Machines AI on Monday announced the launch of Aurora, a multilingual speech-to-text model, built for the Banking, Financial Services, and Insurance (BFSI) sector.
Blue Machines AI attracted widespread attention earlier this year, following a live, unscripted, hour-long ‘AI-versus-human’ debate on television, showcasing its real-time enterprise voice-AI capabilities.
Announcing the launch of a multilingual speech-to-text model tailored for the BFSI sector on Monday, Blue Machines said Aurora is designed for real-time financial conversations in India, where customers frequently switch languages, combine English financial terminology with regional languages, and communicate over noisy or low-bandwidth telephone connections.
Blue Machines AI Chief Technology Officer, Abhishek Ranjan, noted that building speech intelligence for BFSI requires more than generic transcription.
The model has been optimised for multilingual speech, low-latency inference and high-concurrency environments, Ranjan said adding it is evaluated on ability to accurately recognise the entities that drive financial workflows, not merely the surrounding sentences.
According to the company, Aurora was evaluated against leading speech-to-text models using consistent audio inputs and scoring methodology. Blue Machines AI claimed its internal evaluation showed that Aurora delivers higher accuracy at lower latency and is purpose-built for streaming, real-time BFSI conversations.
The datasets covered banking, lending, insurance, collections and customer-servicing conversations. They included Indian English, Hindi, Hinglish, multilingual and code-mixed speech, regional pronunciation patterns, background noise and telephony audio.
“Aurora reflects our commitment to building sovereign AI infrastructure for Indian enterprises,” Nirmit Parikh, Founder and CEO, Blue Machines AI said.
By building Aurora in India, Blue Machines is offering financial institutions speech intelligence designed for how their customers naturally communicate, while ensuring greater control over their data, models and customer interactions, Parikh added. PTI MBI DRR
