California-based SoundHound AI is working with Israeli firm Kardome to enable multi-zone conversational AI inside cars.

This partnership will leverage Kardome’s spatial hearing AI with SoundHound’s conversational AI technology, transforming in-vehicle voice user interfaces.

Kardome’s technology provides precise spatial awareness, isolating up to six different people’s voices in the vehicle, allowing SoundHound Chat AI Automotive to receive a clear, focused audio stream. This lets the car UI accurately understand the specific intent behind each command, regardless of its origin within the cabin. SoundHound’s natural language processing interprets these isolated commands, delivering contextually relevant responses and ensuring a human-like conversation experience for all passengers.

The collaboration provides intuitive, hassle-free voice interaction for every passenger – no additional hardware is needed. In a market where consumers increasingly demand seamless, intuitive technology, providing a voice user interface that works for everyone in the cabin is becoming a competitive necessity.

Imagine offering an in-car experience where every person, from the driver to the third-row passenger, can effortlessly interact with the vehicle, even in the noisiest of cabins. That’s what Kardome and SoundHound AI are delivering. Their joint offering runs on existing hardware, eliminating the need for extra installations.

This combination hears like a human and responds like one. It recognises who is speaking, filters out distractions, and delivers accurate, real-time responses.

For OEMs, this means delivering a premium, multi-zone voice AI experience without requiring additional hardware.

OEMs know that today’s in-car voice offerings are tuned almost exclusively for the first row. Cabin noise, cross-talk and engine rumble undermine voice recognition accuracy. Scaling to all seats often means installing costly, complex mic arrays.

Kardome’s technology (www.kardome.com/spatial-hearing) uses algorithms to analyse 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. 

This precise spatial awareness enables SoundHound Chat AI Automotive (www.soundhound.com/voice-ai-products/chat-ai-automotive) to receive a clear, focused audio stream, allowing it to understand accurately the specific intent behind each command, regardless of its origin within the cabin.

SoundHound’s natural language processing interprets these isolated commands, delivering contextually relevant responses and ensuring a genuinely human-like conversation experience for all passengers.

Together, these technologies create a multi-seat voice UI that works out of the box with no rewiring nor new mic arrays.

Kardome’s plug-and-play technology (www.kardome.com/kardome-mobility) combined with SoundHound’s software SDKs and APIs (fork.ai/technologies/audio-processing/soundhound-houndify) streamlines development timelines.

Imagine this: a family road trip. The driver asks the voice assistant to locate a nearby charging station. The teenager in the back seat asks for their playlist. The youngest in the third row wants to know how long it is until arrival. In today’s vehicles, this often leads to frustrated shouting and missed commands, leaving passengers feeling disconnected. With Kardome and SoundHound, the system accurately handles all three requests without confusion. No one shouts. No one is ignored. Every voice is heard.