Translating “Meow”

With all this meowing, testing out MeowTalk, a new cat translation app created by a former Amazon engineer, proved irresistible.

Illustration by Michelle Simpson

My cats didn’t know what to make of the phone held up to their snouts. Basil ignored the microphone altogether, rubbing his cheeks on the corner of my phone and gnawing at the rubbery case. Little Orange wanted nothing to do with it, swatting at my outstretched hand and hightailing it in a huff. I tried following them around the apartment, hunched over, hand with phone outstretched. Being cats, neither cooperated.

The first successful translation happened when I sat back on the couch and patted my lap, signaling Basil to come over and cuddle. He stood up and stretched in his spot on the coffee table and lazily made his way over to me before jumping into my arms and tucking into my chest. I turned on the microphone as he meowed a clear, bright meow, and the translator did its thing. An advertisement for a psychic played, and then the translation was revealed: “I love you!” (The ads disappear if you upgrade to a premium account.) It was a surprisingly validating confirmation of what I already believed this meow to mean.

The idea is of decoding our cats’ utterances is not as implausible as it may seem. Machine-learning systems, which can extract patterns from large data sets, can distinguish between the squeaks that rodents make when they are happy and those that they emit when they are in distress, notes the New York Times.

MeowTalk uses machine-learning software combined with 13 preset vocalizations to distinguish between different vocalizations and identify cats’ meows. The app detects and analyzes cat utterances in real-time, assigning each one an intention, such as happy, resting, hunting, or mating call. My subsequent translations included many more “I love you’s,”
“I’m happy,” and the always useful “Hey, you.” The translations did seem to accurately convey my cats’ moods.

“We’re trying to understand what cats are saying and give them a voice,” says Javier Sanchez, a founder of MeowTalk. “We want to use this to help people build better and stronger relationships with their cats.”

With a rotating cast of feline characters in my apartment—my own cats, plus whatever cats or kittens I happen to be fostering at the moment—there were endless opportunities for translation. The app had a hard time figuring out the squeaks of the six-week-old kittens I was fostering, but MeowTalk allows users to report their feedback if they think the app is getting things wrong. It also uses the sounds it records to refine its algorithm and improve its performance.

In 2021, MeowTalk researchers reported that the software could distinguish among nine intents with 90 percent accuracy overall. In the scientific paper published by the founders, the authors noted that “Cats vocalize in order to convey different emotions and/or intents and although their repertoire/vocabulary may not be universal, it exhibits consistent characteristics on an individual basis.”

The app is better identifying some sounds over others. It was quickest to detect purring, labeling it as “I need to relax,” but I didn’t really need an app to know that. Other sounds, like those indicating happiness or in pain, it confused not infrequently, according to the study.

Though the translations may not always be 100 percent accurate, what’s indisputable is the interest in decoding what our cats are saying. Cohabitating with pets calls for some mutual understanding, and pet translator apps may be a good place to start. Since November 2020, MeowTalk has seen over 17 million downloads worldwide, over 250 million meows recorded, and more than eight million cat profiles created. But while developers work out the kinks, the best way to get to the bottom of your cat’s commentary is by spending time with them. When you form a familial bond with your pet, it doesn’t take an app to know when they are saying “I love you.”

This article originally appeared in the award-winning Modern Cat magazine. Subscribe today!