L-Acoustics announces Source Intelligence, a proprietary voice-separation technology that delivers clearer, more intelligible vocals and enables engineers to work with unprecedented gain before feedback in live performances.
Running as an exclusive licensed application on the L-ISA Processor II and fully integrated into the L-Acoustics system workflow, Source Intelligence provides front-of-house engineers mixing on L-Acoustics PA systems with a groundbreaking tool to clean up vocals on noisy stages and allow performers to move freely across any stage configuration, including in front of the PA, without risking feedback or sacrificing vocal clarity.
The technology was unveiled during the L-Acoustics Keynote 2026 alongside the L1 large-format line array system and the CS1 subwoofer. The event featured a performance by The War on Drugs.
The voice, and nothing but the voice
Source Intelligence uses machine learning to achieve something previously impossible in live sound: continuously identify the voice within a microphone signal and remove everything else. PA bleed, crowd noise, stage instruments, room reverb… all of it is removed in real time, leaving a cleaner, more natural vocal sound without the limitations that have long been part of touring productions. The result is a vocal that preserves the natural tone, character, and intelligibility of the source — a quality difference that has been noticeable to both engineers and listeners in blind tests.
For decades, engineers have had to fight PA bleed and feedback issues by relying on compromise solutions such as notch filters that alter the sound, unpredictable expanders, or stage designs that force performers to stay away from the audience. Source Intelligence removes those limitations: the system continuously listens to and processes the signal, allowing the engineer to focus on the mix instead of fighting feedback, while the artist can move freely across the stage, explains Ryan John, Director of Product Management, Software at L-Acoustics.
A measurable difference
In blind listening tests with both internal and external participants, Source Intelligence consistently achieved the highest rating for vocal quality compared to competing solutions, removing up to 40 dB of non-vocal signal — an immediate and audible difference for both professional engineers and casual listeners. The technology also significantly reduces feedback risk by eliminating the PA bleed and ambient noise that cause it, rather than reacting after feedback occurs.
From arenas to houses of worship
Source Intelligence has been used in the field since spring 2025 across major tours, Broadway productions, and leading houses of worship. Current beta partners include Solotech on the Harry Styles tour, Clair Global on the Benson Boone and Rosalia tours, and PRG on the Broadway production Dog Day Afternoon.
 |
 |
“Source Intelligence gives me a vocal sound like no other. We basically have studio-quality vocals now, which completely changes the game”, says Joey Diehl, FOH engineer for Benson Boone.
The technology is designed for any application where a voice needs to be amplified: touring, houses of worship, corporate events, and theatrical productions. It works with handheld, headset, lavalier, and distant-pickup microphones, and processes up to four channels simultaneously. Each instance can handle one voice at a time and can even be placed in the signal path of a group of channels so that a single instance may serve, for example, all handheld microphones in a corporate workflow.
I’m very impressed with the additional headroom it gives me. I was able to achieve crisp, clean vocals in every situation, including very loud stage environments and actors positioned in front of the PA, comments Cody Spencer, Tony Award-winning sound designer who used the technology on the Broadway production Dog Day Afternoon.
L-ISA Processor II: a growing ecosystem of intelligence
Source Intelligence is part of a growing portfolio of licensed technologies running on the L-ISA Processor II as part of the complete L-Acoustics ecosystem, the same platform that powers L-ISA Immersive Hyperreal Sound, L-Acoustics DJ, Ambiance, and HYRISS.
Each of these software applications is available separately, allowing engineers and production companies to expand the capabilities and flexibility of a processor they already own.
Once installed, Source Intelligence requires no threshold adjustments, ongoing configuration, or changes to existing console workflows or signal routing. End-to-end latency is less than 8.5 ms over MADI, remaining fixed whether processing is active or bypassed, ensuring that automation and snapshot changes never affect system timing. Full PSU, network audio, and DSP redundancy are standard across the L-ISA Processor II platform.
Availability
Source Intelligence is now available as a software subscription through L-Acoustics All Access for the L-ISA Processor II, exclusively for L-Acoustics system deployments.
Image captions:
- LA_Source_Intelligence_1 – L-Acoustics Source Intelligence runs on the L-ISA Processor II as a licensed software subscription, requiring no threshold adjustments, ongoing configuration, or changes to existing workflows or signal routing.
- LA_Source_Intelligence_2 – FOH engineer Sean “Sully” Sullivan, responsible for mixing Bruno Mars, was among the first engineers to deploy L-Acoustics Source Intelligence on a major touring production. Photo: Diwang Valdez
- LA_Source_Intelligence_3 – FOH engineer Jamie Pollock deployed L-Acoustics Source Intelligence on Nine Inch Nails’ Peel It Back Tour, using machine learning-based voice separation to deliver cleaner, more intelligible vocals in real time.
- LA_Source_Intelligence_4 – Source Intelligence runs on the L-ISA Processor II, the same platform powering L-ISA Immersive Hyperreal Sound, L-Acoustics DJ, Ambiance, and HYRISS, with end-to-end latency below 8.5 ms over MADI and full PSU, network audio, and DSP redundancy.
