At the WardsAuto AutoTech 2025 event in suburban Detroit today, Kardome Mobility and SoundHound AI announced a collaboration aimed at offering intuitive, frustration-free voice interaction for every passenger with no additional hardware needed. Their joint solution provides an improved multi-zone voice interface that runs on existing hardware for an in-car experience where each person, from driver to third-row passenger, can easily interact with the vehicle even in the noisiest cabin.

The partners say that OEMs know that today’s in-car voice solutions often fall short. They’re tuned almost exclusively for the first row. Cabin noise, crosstalk, and engine rumble undermine voice recognition accuracy. Scaling to all seats often means installing costly, complex mic arrays. These limitations are barriers to delivering the premium, user-friendly experience that today’s customers expect.

In a market where consumers increasingly demand seamless, intuitive technology, providing a voice user interface (VUI) that truly works for everyone in the cabin is not just a feature—it’s a competitive necessity. They believe it is a smarter, faster path to meet the rising expectations of today’s drivers and passengers. That’s why Kardome and SoundHound believe their collaboration is a game-changer.

At the core of this collaboration is a shared vision of making in-car voice interaction as natural and effortless as talking to a fellow passenger. By integrating Kardome’s Spatial Hearing AI with SoundHound’s Chat AI Automotive, the solution hears like a human and responds like one. It recognizes who is speaking, filters out distractions, and delivers accurate, real-time responses, whether it’s the driver or someone in the third row.

Kardome says the collaboration is driven by its unique ability to handle highly complex acoustic environments. Among the players in spatial voice AI, the company says it stands out for its precision in isolating individual voices, even with overlapping speakers and the noisiest backgrounds. This level of clarity is essential for providing the seamless multi-seat experience that SoundHound aims for in its platform.

For OEMs, this means delivering a premium, multi-zone voice AI experience with just smarter software providing a more intelligent interface.

Kardome’s technology employs advanced algorithms to analyze the acoustic environment within the vehicle, pinpointing the location of each speaker. Creating distinct “audio zones” isolates individual voices and effectively filters out background noise.

The precise spatial awareness provides SoundHound Chat AI Automotive with a clear, focused audio stream, enabling it to accurately understand the specific intent behind each command, regardless of where it originates in the cabin. SoundHound’s natural language processing interprets the isolated commands, delivering contextually relevant responses and ensuring a genuinely human-like conversation experience for all passengers.

Together, the technologies create a multi-seat voice UI that works out of the box. The solution directly addresses key automotive development challenges like multi-zone voice interaction. OEMs can deploy across vehicle classes without adding costs. Rapid integration is enabled by Kardome’s plug-and-play solution and SoundHound’s software development kit and application programming interface to streamline development timelines. The enhanced UX means that improved accuracy reduces user frustration and increases adoption.

The SoundHound collaboration is just the latest for Kardome in bringing spatial and contextual awareness to in-car interactions with its ambient voice AI technology. In March, the company announced that its Spatial Hearing AI technology is available on the Nvidia Drive AGX platform, allowing for voice isolation, speaker identification, and highly accurate speech processing in noisy environments to create superior in-cabin experiences.

“The availability of Kardome’s voice AI innovation supported on Nvidia Drive can enable OEMs to deliver the ultimate in-cabin voice recognition and communication experience,” said Dani Cherkassky, CEO of Kardome. Cherkassky and CTO Alon Slapak co-founded Kardome to change how people interact with machines and explore the true potential of speech recognition to provide a solution for user frustrations with speech recognition and voice command devices.

Running on Nvidia’s Orin in-vehicle computer enables Kardome’s Spatial Hearing AI technology to be more precise with voice recognition and communication, resulting in frustration-free and personalized in-vehicle experiences. The solution locates, identifies, and isolates individual users from up to six zones using a single microphone array in the overhead cabin.

Kardome says its core technologies enable better VUI and ASR (automatic speech recognition) performance. Among its core technologies are speech separation (spatial hearing), echo cancellation, and noise reduction modules that facilitate reliable ASR performance in noisy and multi-speaker scenarios.

The company says an ASR’s ability to accurately translate acoustic speech signals depends on the clarity of the input signal. As a result, noise reduction, echo cancellation, source separation, and other components are added to the VUI to enhance the acquired signal before reaching the ASR.