Sanas Unveils Simultaneous Real-Time Speech-to-Speech Translation

Speech technology vendor Sanas has launched AI-powered Real-Time Speech-to-Speech Language Translation.

Unlike traditional translation technologies that convert speech to text, translate it, and synthesize it back into speech, Sanas' latest innovation uses a proprietary artificial intelligence-based architecture to perform direct, low-latency speech-to-speech language translation. It leverages recent advancements in large language models to enable real-time, omnidirectional translation while preserving speaker identity and emotional nuance. The first supported language pairs include English-Spanish and English-French, with others soon to follow.

"Designed to enhance communication clarity, improve agent performance, and boost customer satisfaction, Sanas empowers businesses to deliver more empathetic and inclusive customer experiences," said Sharath Keshava Narayana, CEO and co-founder of Sanas, in a statement. "This latest leap forward in AI-powered speech technology brings us closer to a world where linguistics and language is no longer a barrier."