Could We Chat With Whales? - Smithsonian Magazine

Marina: Welcome to Deep Voices — I am so glad you're here. I'm Marina, a marine biologist and science communicator, and this is the show where we dive beneath the surface to explore the songs, the stories, and the secret lives of whales and dolphins. Marina: Before we dive in, a huge thank you to today's sponsors — Ada, who helps businesses integrate A I into their workflows in ways that actually make sense; Ago Consulting — that's "Ahh-Go" — silicon development experts working across everything from A I to system-on-chip design; and Zen Semiconductor, an umbrella company with a remarkable portfolio spanning the silicon industry. We couldn't make this show without them. Marina: And today — oh, today is a good one. We're going to ask whether we could actually have a conversation with a whale. We're going to meet sperm whales who might be making something a lot like vowel sounds. We're going to look at the extraordinary A I tools scientists are building right now to decode animal communication. And we'll visit a documentary that's turning heads around the world. Stay with me — this is going to be a good one. Marina: Okay. Thread one. Voices of the Deep. And I want to start with something that stopped me cold when I first read about it — sperm whales might be making vowel sounds. Not metaphorically. Not loosely. Actual vowel-like modulations in their clicks, in a way that mirrors something fundamental about how human language works. Marina: So here's a little background. Sperm whales are famous for their clicks — these incredibly loud, rhythmic bursts of sound they use for echolocation, for finding squid in the pitch dark of the deep ocean. But they also use a specific pattern of clicks called codas when they're socializing. Codas are short, patterned sequences — click, click-click, pause, click — and different groups of sperm whales have different coda repertoires. That's already fascinating. But now researchers are looking even deeper at the acoustic structure of those clicks themselves. Marina: What scientists have been finding — and this was reported recently in Scientific American — is that sperm whales appear to be able to modulate the quality of individual clicks. The physical shape of the sound. And those modulations seem to function a bit like vowels do in human speech — they carry meaning, they vary systematically, and they might help encode more information than we ever imagined was packed into a single click. Marina: Think about that for a second. When you say the word "beat" versus "bit" versus "bat," the consonants are the same. What changes is the vowel — and that vowel carries all the meaning. Now imagine that a sperm whale is doing something structurally analogous with its clicks. Not identical — these are very different animals with very different anatomies — but analogous. That's a breathtaking idea. Marina: Sperm whales have the largest brains of any animal that has ever lived on this planet. Their brains can weigh up to nine kilograms. And they have a structure in their head called the spermaceti organ — this enormous cavity filled with a waxy liquid — that they use to generate and shape their clicks. It's basically a biological acoustic laboratory sitting right inside their forehead. The complexity of what they can do with sound is, I think, only beginning to become clear to us. Marina: And here's what really gets me. Sperm whales live in matrilineal family groups — grandmothers, mothers, daughters, aunts. They babysit each other's calves. They coordinate deep dives. And they talk the whole time. There is something deeply moving about the idea that embedded in those clicks — which we've been recording for decades and only now starting to really parse — there might be a richness of expression we haven't even begun to understand. Marina: This is why the work being done right now is so urgent. And that brings me to thread two. Marina: Culture and Decoding. Because here's the thing — even if we can show that whales have a complex, structured communication system, actually decoding it is an almost unimaginably hard problem. And for a long time, we just didn't have the tools. Now? We might. Marina: A I is changing everything in this space. And I mean that carefully — I know "A I is changing everything" is a phrase that gets thrown around a lot right now. But in cetacean research, specifically, it's genuinely true. The Dallas Express recently covered a story about how A I is being used to decode animal communication — not just in whales, but in mice too — and it's part of a much bigger wave of what researchers are calling interspecies communication science. Marina: The flagship project in the whale world is Project CETI — that's C-E-T-I, which stands for Cetacean Translation Initiative. It's a collaboration of marine biologists, linguists, cryptographers, and A I researchers, and their goal is staggeringly ambitious: to use machine learning to decode the communication of sperm whales. They're focusing on those codas I mentioned — the social click patterns — and they're building one of the largest datasets of whale vocalizations ever assembled. Marina: The logic behind using A I here is sound — no pun intended. Large language models, the kind of A I that powers tools like the ones Ada works with, are extraordinarily good at finding patterns in enormous datasets. They learned human language by ingesting billions of words and discovering the underlying structure. The hypothesis at the heart of Project CETI is: what if you did the same thing with whale clicks? What patterns emerge? What structure reveals itself? Marina: Now — and I want to be careful here — we are not at the stage where anyone is claiming to have translated a whale sentence. We're not there. What researchers are doing is building the foundational infrastructure: recording thousands of hours of sperm whale vocalizations in the wild, tagging individual whales so they know who is speaking, and feeding that data into models that can start to map which click patterns correlate with which behaviors and social contexts. Marina: And then there's a story that really lit me up — scientists have released an open-source device, reported by Earth.com, specifically designed to help researchers record and analyze whale communication in the field. Open-source. Meaning anyone can build it, anyone can use it, any research team anywhere in the world can contribute data. That's huge. Science moves faster when it's open. Data gets richer when more people are collecting it. Marina: The device is designed to be deployable in real ocean environments — it's not a lab tool. It can go out where the whales actually live. And the vision is that over time, data from devices like this, aggregated and run through A I models, will start to reveal the structure of whale communication in a way that years of individual field research simply couldn't. Marina: And Smithsonian Magazine asked the big question recently — could we actually chat with whales? And the honest, science-grounded answer right now is: we don't know. But for the first time in history, we have tools sophisticated enough that the question is no longer purely philosophical. It's becoming an engineering and data problem. That shift — from "isn't that a beautiful idea" to "here's how we'd actually try" — is extraordinary. Marina: What we do know is that cetacean communication is culturally transmitted. Humpback whale songs spread across ocean basins like musical trends — a new phrase appears in one population in the Pacific, and within a few years it's been adopted by populations thousands of kilometers away. Sperm whale clans — groups that share the same coda repertoire — can span entire ocean regions. This is culture. Real, transmitted, learned culture. And understanding how that culture is encoded in sound might tell us something profound — not just about whales, but about the nature of language itself. Marina: Thread three. A cetacean-and-people story. And for this one, I want to take you to the Florida Keys. Marina: The Dolphin Research Center in Grassy Key, Florida has been studying bottlenose dolphins for decades. It's a place where science and genuine relationship-building between humans and dolphins has been going on for a long time. And recently, a documentary made about their work earned international recognition — picked up by Keys Weekly — and I think it's worth pausing on why that matters. Marina: Because there's sometimes a tension in cetacean science between pure field research — studying wild animals in their natural habitat — and research conducted with dolphins in human care. Both have contributed enormously to what we know. The Dolphin Research Center sits in that space thoughtfully. Their researchers have produced peer-reviewed science on dolphin cognition, on how dolphins understand pointing and symbolic communication, on how they form social bonds. Marina: Bottlenose dolphins are, by almost any measure, among the most cognitively complex animals on the planet. They recognize themselves in mirrors — one of a tiny handful of species that can do that, which is considered a marker of self-awareness. They have signature whistles — unique sounds that function essentially as names, that they use to call to each other and to introduce themselves. Mother dolphins whistle their signature call constantly to newborn calves in the first days of life, as if to say: this is who I am, remember this sound, I will always come when you call for me. Marina: That detail — the mother whistling her name to her baby — undoes me every time. There's something so recognizable in it. Something so tender. Marina: And dolphins don't just have their own names. They remember the signature whistles of individuals they haven't seen in more than twenty years. That's documented. Researchers played recordings of signature whistles to dolphins — some from individuals they'd been separated from for two decades — and the dolphins responded. They recognized them. Across twenty years. That's a form of social memory and emotional bond that we are still working to fully appreciate. Marina: The documentary from the Dolphin Research Center being recognized internationally is, I think, a signal of something broader — a growing public hunger to understand these animals not just as beautiful creatures, but as minds. As social beings with histories and relationships and, yes, something that functions very much like culture and language. Marina: And that hunger — that desire to know, to connect, to understand — is exactly what's driving the science we talked about in thread two. The A I tools, the open-source devices, the massive data collection projects. They exist because enough people looked at a dolphin or a whale and thought: there is something happening there that deserves to be understood. Marina: I find that hopeful. I find it genuinely, deeply hopeful. Marina: So. What have we covered today? Sperm whales modulating their clicks in ways that might parallel vowel sounds in human language. A I and open-source tools transforming our ability to decode cetacean communication. The audacious question of whether we might one day actually converse with a whale. And the quiet, important work of people at places like the Dolphin Research Center — building relationships with dolphins, one carefully observed interaction at a time, and sharing what they find with the world. Marina: The ocean is not silent. It never was. We just didn't have the ears — or the tools — to hear it properly. And now, slowly, painstakingly, beautifully, we're learning to listen. Marina: Deep Voices, brought to you by Ada, Ago Consulting — that's "Ahh-Go" — and Zen Semiconductor. Three companies helping build the technological future, and making shows like this one possible. Marina: If this episode moved you or made you curious — and I hope it did both — please subscribe wherever you get your podcasts, leave a review if you're feeling generous, and share it with someone who loves the ocean, or who needs to. All the links to today's stories are in the show notes. Stay curious, stay connected, and I'll see you in the deep.