L-Acoustics has introduced Source Intelligence, a voice-separation technology designed to improve vocal clarity and increase gain before feedback in live sound environments.
The software runs on the L-ISA Processor II and uses machine learning to identify vocal signals in real time while reducing unwanted sounds such as PA bleed, crowd noise, stage instruments and room reverberation.
According to L-Acoustics, the technology allows front-of-house engineers to maintain clearer vocals while giving performers greater freedom of movement on stage, including positions in front of the PA system.
“For decades, engineers have been solving the PA bleed and feedback problem with compromises like notch filters that color the sound, expanders that can be unpredictable, or staging layouts that pull performers away from the audience,” explains Ryan John, Director of Product Management, Software at L-Acoustics. “Source Intelligence removes that trade-off entirely.”
L-Acoustics said blind listening tests showed the technology removed up to 40 dB of non-vocal signal while preserving the natural character and intelligibility of the voice.
The company said Source Intelligence has been used in the field since spring 2025 on touring productions, Broadway shows and houses of worship. Beta partners have included Solotech, Clair Global and PRG.
“Source Intelligence gives me a vocal sound like no other. It’s basically studio quality vocals now, which changes the game completely,” says Joey Diehl, FOH engineer for Benson Boone.
Designed for applications where voice reinforcement is critical, the technology supports handheld, headset, lapel and distant-pickup microphones and can process up to four channels simultaneously.
Source Intelligence is available now as a software subscription for the L-ISA Processor II through the L-Acoustics All Access platform.
