Skip to main content

Translation technology may let humans speak with dolphins

Dolphins have long been considered by scientists to be the most intelligent animals on the planet (aside from humans, of course). But soon, with the help of newly developed underwater translation software, our two species may actually be able to talk to each other.

Armed with a waterproof computer, divers may soon be able to decipher the chirps of dolphins, then create and project an appropriate response, all in real time, reports New Scientist.

Recommended Videos

Dubbed Cetaccean Hearing and Telemetry (CHAT), the project is being undertaken by Denise Herzing, founder of the Wild Dolphin Project, and Thad Starner, an artificial intelligence researcher at the Georgia Institute of Technology in Atlanta. The end-goal of the CHAT program is to “co-create” a language that uses the natural sounds of wild dolphins, which can then be employed to talk with our finned brethren.

Humans have been able to communicate with dolphins since the 1960’s. Studies have shown that dolphins can learn up to about 100 human words, and be able to decipher the difference between similar commands, like “bring the surfboard to the man” and “bring the man to the surfboard.”

According to Herzing, past attempts to talk with dolphins have been primarily one-way. “They create a system and expect the dolphins to learn it, and they do, but the dolphins are not empowered to use the system to request things from the humans,” she says. Because of this, Herzing and her colleagues have been working on a two-way communication system since 1998. Those attempts, while somewhat successful, weren’t “dolphin friendly” enough, Herzing says.

With the help of his students, Starner is currently building a prototype device that includes a “smartphone-sized computer” and two hyrdophones, which can detect the sounds of dolphins. Ultimately, a diver can carry the device in a waterproof case that will be strapped to the chest. When the hydrophone pics up dolphin chatter, an LED in the diver’s mask will light up. The diver can then use an on-board Twiddler, a kind of keyboard-mouse combo, to respond to the dolphin.

The challenges of creating such a system are, as one might imagine, immense. For starters, dolphins can produce sounds at frequencies of up to 200 kilohertz, far higher than the human ear can hear. Dolphins change their pitch, and hold a note for extended periods of time. They also project their sound in different directions without turning their heads. All of these factors must be considered in the development of the CHAT translation technology.

Amidst these challenges, Herzing and Starner hope to decipher the dolphin tongue, testing for which will begin in the middle this year. The beginning phase requires projecting eight choice “words” to a group of wild Atlantic spotted dolphins — things like “seaweed — and figuring out if the dolphins mimic the words. If that proves successful, the team can then move on to the daunting task of trying to translate the fundamentals of dolphin language by associating “words” with behaviors and objects. For this, the team will also use a type of software called a “pattern detector,” which helps find useful information in a mishmash of data.

Even if the team has developed an air tight plan, success remains a long shot.

“We don’t even know if dolphins have words,” Herzing admits to New Scientist. That said, she adds, “We could use their signals, if we knew them. We just don’t.”

Andrew Couts
Features Editor for Digital Trends, Andrew Couts covers a wide swath of consumer technology topics, with particular focus on…
Google’s AI agent ‘Big Sleep’ just stopped a cyberattack before it started
Sundar Pichai

Google's AI agent, dubbed Big Sleep, has achieved a cybersecurity milestone by detecting and blocking an imminent exploit in the wild—marking the first time an AI has proactively foiled a cyber threat. Developed by Google DeepMind and Project Zero, Big Sleep identified a critical vulnerability in SQLite (CVE-2025-6965), an open-source database engine, that was on the verge of being exploited by malicious actors, allowing Google to patch it before damage occurred. “We believe this is the first time an AI agent has been used to directly foil efforts to exploit a vulnerability in the wild,” the company said.

Why it matters: As cyberattacks surge—costing businesses trillions annually—this breakthrough shifts defense from reactive patching to AI-driven prediction and prevention. It gives security teams a powerful new tool to stay ahead of hackers, potentially saving devices and data worldwide. CEO Sundar Pichai called it "a first for an AI agent—definitely not the last" according to Live Mint.

Read more
Google confirms merging Chrome OS and Android into one platform
Google Chrome app on s8 screen.

Why it matters: Google's push to blend Chrome OS and Android could supercharge affordable laptops like Chromebooks, making them more versatile for work and play. This move echoes Apple's seamless ecosystem across iPadOS and macOS, potentially shaking up the PC market where Windows dominates but innovation lags.

What's happening: In a bombshell interview, Google's Android ecosystem president Sameer Samat outright confirmed the company is "combining Chrome OS and Android into a single platform. This follows months of rumors and aligns with Android 16's new desktop-friendly features, like proper windowing and external display support. But then Samat later clarified on X that it's not a full-on merger killing Chrome OS; instead, it's about weaving Android's tech stack deeper into Chrome for better app compatibility and hardware efficiency.

Read more
WeTransfer backlash highlights need for smarter AI practices
A pair of hands using a keyboard on a laptop.

A recent update to WeTransfer’s terms of service caused consternation after some of its customers feared that it meant content from files uploaded to the popular file-sharing service would automatically be used to train AI models.

But the Netherlands-based company insisted on Tuesday that this is not the case, saying in a statement that it "does not sell user content to third parties,” and nor does it "use AI in connection with customer content.”

Read more