Breaking barriers with Babel OS: Timekettle’s next leap in language technology

For nearly a decade, Timekettle has been synonymous with hardware innovation in translation devices, producing tools that help people connect across language barriers. Now, with the launch of Babel OS, the company is making a statement that the future of cross-language communication lies in the seamless fusion of advanced software and hardware.

Babel OS has the potential to be a complete game-changer in communication. From real-time, emotionally resonant translations to customizable lexicons tailored for specific scenarios, Babel OS redefines what’s possible in translation technology. But what does this mean for Timekettle, its users, and the broader industry?

We wanted to know more, so we sat down for a chat with Timekettle’s founder and CEO, Leal Tian, at CES 2025 in Las Vegas. We were curious about the vision behind Babel OS, the challenges of blending cutting-edge software with innovative hardware, and how these advances are reshaping the way we connect across languages. 

Q. Timekettle is known for its groundbreaking hardware, but Babel OS really shows how important your software innovations are, too. What’s it been like balancing advancements in both hardware and software, and how does Babel OS bring it all together?

To us, the most important thing is to bring people a new experience,  so we’re not focusing only on hardware, software, or AI alone. What we’re really concerned about is how people can really communicate, even if they’re speaking different languages.

In the past, we’ve always been known for our earbuds and hardware, but at least 50% of the work is done by the software. For example, if you’re using our earbuds, the embedded software, the algorithm for noise cancelation, and the communication protocol all belong to the software side.

This year, we decided to push the software to the forefront and let people know how we are working to ensure they have a smoother experience. That’s why we released Babel OS. For us, it’s not about balancing hardware and software — they’re part of the same system, working together to provide a unique and immersive experience.

Q. In a past interview, you mentioned the Babel Fish from The Hitchhiker’s Guide to the Galaxy as an inspiration for Timekettle. How did that idea influence the development of Babel OS, and how close do you believe you are to bringing that science fiction vision closer to reality?

Yes, I’m a sci-fi fan, and The Hitchhiker’s Guide to the Galaxy is a classic that everybody knows. If you visit our office, you’ll even find a meeting room named Adams, after the author. It’s an interesting concept that appears in this story, as well as in Star Trek and many other sci-fi films, where translators are everywhere, allowing people to talk to each other or even with aliens. The inspiration comes from this kind of imagination — people talking to each other without language barriers. It’s a beautiful thought.

Our mission is to make the world have fewer language barriers. And the final goal is just like the Babel Fish in the movie — you put it in your ear, and you don’t have to do anything. You can talk to anyone, just like you’re talking to a close friend. And with Babel OS, we show our respect for the novel.

Q. Babel OS introduces features like AI Semantic Segmentation and custom lexicons. How do these advancements transform the experience of real-time translation compared to existing solutions?

In our opinion, in the past, tools like Google Translate and similar software or hardware were focused on translation, not communication. For example, think of the camera on the back of your phone. When you use it, the goal isn’t just to take a picture — it’s to capture emotion and information. That’s a deeper level of the human instinct. It’s the same with communication. People want to connect, so they need translation, but translation is just a tool and doesn’t convey the instinct.

As humans, we are social animals. Looking back, it becomes clear that everything should focus on how we can provide immersive communication, not just translation. Software or hardware used in the past was more like consecutive translations, where people took turns or passed things back and forth to talk. It wasn’t natural. Our goal, on a technological level, is to achieve simultaneous interpretation.

With Babel OS, we’ve successfully integrated technologies like speech recognition and speech processing. For example, on the front end, we process the voice to ensure the pickup is clear enough to translate. And while translation accuracy is important, so is speed. If I spoke to you and you only received what I said every 10 seconds, it would feel awkward. It’s not natural communication.

Babel OS helps our products deliver this groundbreaking experience, making it feel like you have a real interpreter beside you. We’re continuously improving aspects like accuracy, speed, and naturalness, including features like AI voice cloning. All of this is aimed at achieving the ultimate goal: creating a solution like the Babel Fish, enabling truly natural communication across languages.

Q. One of the most fascinating aspects of Babel OS is its ability to replicate human emotion and tonality. What challenges did you face in developing this feature, and how do you see it impacting cross-language communication?

Voice cloning and capturing emotions is a very big project for us. It’s not something our company can develop entirely on its own, so we use a combination of our own technology and third-party technologies.

For example, if you want to analyze what someone is saying, including their emotions — whether they’re angry, happy, or something else — you must first detect those emotions. Then, you move on to speech synthesis, or what we call TTS, which is text-to-speech. At this stage, you can add features to guide the AI in replicating the emotions detected in the earlier step.

The result is not only copying the authentic voice but also capturing the emotions. It’s a whole procedure, and it’s not something accomplished by us alone.

Q. Babel OS is running on devices like the W4 Pro Earbuds and the X1 Interpreter Hub. How do you think this combination of smart software and innovative hardware will make a difference in people’s day-to-day lives?

We hope this product will be used everywhere in the future. When you go to a hospital, live abroad, travel, or attend a business meeting, it should be there. The final goal is for it to be so immersive that you’re not even aware of its existence. As I mentioned, communication is a human instinct. Most of the value we create and the connections we make come from speaking. That’s why we see this as a fundamental device for the future.

Q. Babel OS feels like a major leap forward in AI translation. How do you see this innovation shaping both Timekettle’s future and that of the broader industry of cross-language communication?

It’s a big step because it integrates all the technology we’ve developed, making communication much smoother. As I mentioned, we’re moving toward the vision of the Babel Fish in the future. Right now, this is version 1.0, but maybe next year, you’ll see version 2.0 with many more features. It’s a process, and it takes time.

Babel OS is available now and powers Timekettle’s latest device lineup, including the new W4 Pro Earbuds, the WT2 Edge Earbuds, the X1 Interpreter Hub, and the T1 and T1 Mini Handheld Interpreters. These devices, enhanced with Babel OS, offer real-time, human-like translations across 40 languages and 90 accents, optimizing the communication experience.

Timekettle is currently showcasing Babel OS at CES, where attendees can experience its groundbreaking features and learn more about the next steps in cross-language communication. Babel OS marks a significant step forward for Timekettle, but as CEO Leal Tian notes, this is just the beginning. With ongoing updates and future iterations in the works, the future of communication is closer than ever.