The free game gives players five English words to guess, but every clue is a translation in one of twelve languages, and each language can be used only once.
Translation company Tomedes has released Parley, a free daily word puzzle that trades the familiar five-letter grid for a multilingual guessing game. Players have to identify five English words, but the only clues on offer are translations of those words across twelve languages, and the whole puzzle turns on a single constraint: each language can be spent just once.
The launch lands as the daily-puzzle category keeps expanding. New York Times Games puzzles were played 11.2 billion times in 2025, and the Times has announced an NBC television adaptation of Wordle, a measure of how far the once-niche format has traveled. Parley is a bet that the next wrinkle in the genre is language itself.
Each day’s puzzle presents five hidden English words and a row of twelve flags. Tapping a flag reveals the target word translated into that language and plays the pronunciation aloud. Because every language can be used only once across all five words, players are managing a pool of twelve clues against five answers. Wrong guesses reveal letters, and the score, capped at fifteen, climbs the fewer clues a player spends.
That scoring rule is what pushes Parley from vocabulary quiz toward strategy game. Solving a word is simple if you spend enough clues. Solving it cheaply is the real challenge. Players who treat the twelve languages as a resource, holding back cognate-rich options such as Spanish or French for the hardest word and burning unfamiliar scripts early, tend to come out ahead.
The clues themselves rest on Tomedes’ translation platform, MachineTranslation.com, and the company says that is deliberate. Rather than drawing each translation from a single model, the platform uses a mechanism it calls SMART, which compares the outputs of 22 AI models and selects the translation that most of them agree on.
“People assume a translation is simply right or wrong, but ask a dozen AI models for the same word and you often get more than one answer,” said Rachelle Garcia, AI Lead at Tomedes. “A game is a low-stakes way to show that. The clue you see in Parley is the one the majority of the models agreed on.”
According to the company, that consensus step is what keeps the clues dependable. Tomedes says its internal testing found the approach, which requires a majority of the 22 models to agree before any translation is delivered, cuts critical translation errors to under 2% and reduces overall error risk by roughly 90% compared with relying on a single model. In a puzzle, one wrong clue can make a round unsolvable, so the reliability of the underlying translations matters more than it would in a typical casual game.
The daily structure borrows from a proven retention model. Duolingo surpassed 50 million daily active users in late 2025 on the strength of its one-lesson-a-day streak loop, and Parley adopts the same rhythm: one puzzle per day, a shareable result card, and a round meant to last about a minute. Unlike an anagram game, it also leaves players having seen five words rendered across a dozen languages, with audio, which gives the format a learning angle most Wordle-style clones lack.
Whether Parley reaches the audience of the genre’s biggest names is an open question, and most new daily games never do. As a design idea, though, it does something the category rarely attempts. It takes the normally invisible work of translation and makes it the thing players are engaging with.
Parley is available now at tomedes.com/games/parley. It is free to play, resets every day, and requires no account.
Aron Wrighthandier has opinions about gaming news and trends. Informed ones, backed by real experience — but opinions nonetheless, and they doesn't try to disguise them as neutral observation. They thinks a lot of what gets written about Gaming News and Trends, Upcoming Game Releases, Competitive Play Insights is either too cautious to be useful or too confident to be credible, and they's work tends to sit deliberately in the space between those two failure modes.
Reading Aron's pieces, you get the sense of someone who has thought about this stuff seriously and arrived at actual conclusions — not just collected a range of perspectives and declined to pick one. That can be uncomfortable when they lands on something you disagree with. It's also why the writing is worth engaging with. Aron isn't interested in telling people what they want to hear. They is interested in telling them what they actually thinks, with enough reasoning behind it that you can push back if you want to. That kind of intellectual honesty is rarer than it should be.
What Aron is best at is the moment when a familiar topic reveals something unexpected — when the conventional wisdom turns out to be slightly off, or when a small shift in framing changes everything. They finds those moments consistently, which is why they's work tends to generate real discussion rather than just passive agreement.