AI-Media has partnered with AudioShake, a leader in real-time audio separation technology, to advance the capabilities of multilingual accessibility in live broadcasting.
The collaboration strengthens Lexi Voice, AI-Media’s AI-powered live voice translation solution, through the integration of AudioShake’s advanced SDK. Designed to isolate announcer commentary from background noise, AudioShake empowers Lexi Voice to operate with even greater precision in challenging live environments such as sports, concerts and news coverage.
In fast-paced scenarios where audio complexity is high, such as cheering crowds, music, or in-game effects, AudioShake’s technology cleanly separates spoken dialogue from the surrounding noise. This gives Lexi Voice a clearer signal to process, resulting in sharper real-time captions and more accurate AI-generated voice translations.
Tony Abrahams, CEO of AI-Media, said: “This partnership with AudioShake is a game-changer for live sports and event broadcasting. The ability to isolate and clean up sports commentary in real-time while delivering AI-generated translations through Lexi Voice will redefine the viewing experience for global audiences.”
Once translated, announcer speech is re-voiced using humanlike AI voices and mixed back into the original broadcast audio. This gives an immersive viewing experience in the viewer’s preferred language without losing the live atmosphere and energy of the event.
