Kardome

Home
Israel
Tel Aviv
Kardome

Hearing is critical. Understanding is everything. Voice is the interface of the future.

That’s why we developed Voice AI that hears and understands like people do. It makes voice UI work as it should, providing frustration-free voice experiences anywhere, anytime for AI products that people love to use. Kardome gives your voice-integrated products the ability to hear and localize sound sources, identify who’s speaking, and understand what they mean in context, for natural, intuitive

voice interactions that perform reliably in the most complex environments: Powered by our Spatial Hearing AI and Cognition AI. Visit our Website kardome.com to learn more or email us [email protected]

South Korea Headquarters:
Seoul, Seocho-Gu Gangnam-Daero 455
Taeyoung Dessian Loube A-903

03/09/2026

Most in-car voice systems have one blind spot: the rest of the car. Passengers, kids in the back seat, and whoever’s riding shotgun talk to systems that ignore them, confuse who said what, or miss the context behind the request.

Kardome fixes that. Seat-level accuracy. No wake word needed. No added hardware. No cloud round-trip for the requests that should be instant — just spatial hearing and on-device cognition that knows who’s speaking, where they’re seated, and what they need.

🏆 The AutoTech judges agreed: Kardome’s In-Vehicle Voice AI won the 2026 In-Vehicle Experience Award.

We’ll be in Detroit this September for Automotive News Congress and hosting a private cocktail reception for the people shaping the future of the in-cabin experience.

See Kardome in action and meet our CEO and members of our product and business development teams for in-depth conversations about the technology and its automotive applications.out the technology and its automotive applications.

Interested in joining us in Detroit? Send us a DM to request an invitation.

25/08/2026

Voice AI has become remarkably good at understanding what we say.

The next challenge is understanding what we mean — in the context of the real world.

Who is speaking?
Where are they?
Are they talking to the device?
What is happening around them?
And does the interaction require an action at all?

In a new interview with NewElectronics, Kardome CEO Dani Cherkassky discusses why the next generation of voice interfaces will depend not only on smarter AI, but on context, awareness and intent — and why advances in edge AI are finally making that possible.

“The goal isn't to force people to communicate in a way machines understand. It's to build machines that understand people the way people naturally communicate, with context, awareness, and intent.”

Read the full interview:
https://hubs.ly/Q04vdjnN0

07/08/2026

Our CEO Dani Cherkassky ends his latest piece with a question worth sitting with:
The question for OEMs and developers isn't "how smart is your model?" It's "how present is your interface?"

You can put a frontier model in a pair of glasses and still ship something that can't tell who in the room is talking to it. Presence is a different problem than intelligence, and it's the one holding physical AI back.

📖 Read the full article by Dani Cherkassky here: https://hubs.ly/Q04sjrYC0

30/07/2026

Everyone is talking about bigger AI models. But what if the real challenge isn't intelligence? What if it's awareness?

Traditional voice AI was designed to recognize speech. The next generation needs to understand the real world: who is speaking, where they're speaking from, and what matters in the moment.

In our latest blog, we explore how cognitive awareness goes beyond traditional ASR and how combining Spatial Hearing AI with Cognition AI enables more natural, context-aware voice interactions.

Link in the comments.

27/07/2026

Kardome is honored to be recognized as an Automotive News PACE Award finalist for redefining in-vehicle voice AI.

Our demo showcases true multi-user, spatially intelligent voice interaction:bringing human-level understanding, seamless multi-zone engagement, and robust performance to every seat.

See how Spatial Hearing AI and Cognition AI set a new standard for in-cabin user experience, platform scalability, and brand differentiation: fully on-device, cost-efficient, and ready for the next generation of automotive innovation.

More about Kardome's In-Vehicle Voice AI in the comment link👇

16/07/2026

Physical AI Requires More Than Voice Recognition—It Requires Context

For decades, Voice AI innovation has focused on one goal: recognizing speech more accurately.

But as AI moves beyond smart speakers into TVs, appliances, robotics, and other physical devices, recognition alone is no longer enough.

Physical AI must understand context.
Who is speaking?
Is the speech directed at the device?
What is happening in the surrounding environment?
How should the device respond?

Without contextual understanding, even the most advanced AI systems struggle in the real-world environments where consumers actually use them.

In our latest article, explore why context is becoming the missing layer in Voice AI—and why it will be critical to the next generation of Physical AI experiences.
Read more: https://hubs.ly/Q04pNTn70

08/07/2026

Recently in Korea, we convened with leading consumer electronics OEMs to talk about where Voice AI goes next.

The biggest takeaway: AI in the physical world remains trapped in a "command-processing" loop. To reach the next level, voice technology needs to do more than just transcribe; it needs to perceive and understand. We're talking about AI that understands spatial context, maintains conversational continuity, and recognizes intent in real time, without requiring a cloud round trip.

That's the vision we're building at Kardome, and it was a privilege to explore this with the teams defining the next generation of voice-led devices. Thank you to DJ and the Korea team for bringing us all together.

Hearing is critical. Understanding is everything.

06/07/2026

When the screen disappears, audio becomes the interface — and that changes everything about the mic system.

New Counterpoint data (via AudioXpress) shows display-less smart glasses grew 210% YoY in Q1 2026, the fastest-growing category in intelligent eyewear. No display means the wearer speaks commands, hears responses through near-ear speakers, and relies on the microphone array to feed environmental context to an AI assistant.

That's a genuinely hard acoustic problem, and it comes down to three things:

- Spatial localization: With no screen to point at, the system has to know which voice matters: the wearer, the person they're facing, or the crowd behind them. Attributing sound to a location is what makes features like conversation focus work, rather than amplifying everything at once.

- Voice isolation: Open-ear speakers sit millimeters from the mics, so the glasses' own playback bleeds back in alongside wind, traffic, and surrounding conversations. Clean speech pickup means separating the target voice from all of it, in real time.

- On-device processing: Always-listening for an assistant can't survive a cloud round-trip on every utterance. Latency, battery budget within a frame, and the privacy expectations around a device that hears your surroundings all point in the same direction: the processing has to happen on the glasses.

All this decides whether the glasses actually work, and it's the problem we spend our days on at Kardome.

25/06/2026

Most devices can speak. Very few can truly hear.

That gap — between a device that processes voice commands and one that genuinely understands who is speaking, where they are, and what they mean — is exactly what Kardome was built to close.

We're proud to be named Natural Language Recognition Solution of the Year by the 2026 AI Breakthrough Awards, recognized for on-device Voice AI that performs in the real world, not just the lab.

For OEM teams building the next generation of in-vehicle and smart home experiences, this is the technology that makes voice UI actually work.

Hearing is critical. Understanding is everything.

18/06/2026

Everyone is racing to add LLMs to voice products, but here is the uncomfortable truth: voice AI fails not because the model isn't smart, but because it's "deaf" to the real world until triggered.

For OEMs, relying solely on cloud-based LLMs isn't just a latency issue; it's a cost and differentiation trap.

As Kardome CEO Dani Cherkassky argues in his latest piece in The AI Innovator, the future of voice AI isn't about the biggest model. It's about a smarter distribution of intelligence: on-device cognition that enables spatial awareness, continuous hearing, and immediate responses.

The winners in voice AI won't be the companies with the largest parameter, but those who deliver devices capable of human-like conversation that work in real-life environments: overcoming noise, handling interruptions, and navigating overlapping conversations.

Is your product roadmap prioritizing edge-first context, or are you still tethered to the cloud? Let us know in the comments below.

Address

Yisra'el Bak Street 3, Tel Aviv-Jaffa
Tel Aviv
6701908

Website

http://kardome.com/

Alerts

Be the first to know and let us send you an email when Kardome posts news and promotions. Your email address will not be used for any other purpose, and you can unsubscribe at any time.

Contact The Business

Send a message to Kardome:

Want your business to be the top-listed Computer & Electronics Service in Tel Aviv?