Bluesky gets the lion\u2019s share of press when it comes to Jack Dorsey\u2019s non-Twitter projects, so it might be easy to forget he was also one of the developers of Square, the ubiquitous point-of-sale system that has a number of noteworthy subsidiaries like Cash App, Afterpay, and Tidal.<\/p>\n
Square also changed its name to Block, Inc. in 2021. Perhaps sensing a way to acquaint the unfamiliar with the rebranded business by way of earned media hits, Block just released an AI model with a bit of a twist.<\/p>\n
The model\u2019s name is Dessa and Block\u2019s announcement post<\/a> says it was \u201ctrained from scratch on nothing but human conversation.\u201d Block claims that \u201ctalking with it feels like talking with a person\u2026full of emotion, nuance, pauses, and a natural cadence.\u201d<\/p>\n As reported in The Verge<\/a>, Dessa processes and generates audio directly using speech-to speech architecture rather than converting input speech to text and generating a response like conventional voice models. This duplex architecture also allows Dessa to speak and listen at the same time, which should prevent some of the abrupt subservient silences most other AIs offer the moment a user pipes up.<\/p>\n Block understands that, for things like these, hearing is believing, so the company put out a number of audio examples of Dessa speaking to showcase its abilities.<\/p>\n Take this video<\/a> on X, posted by Dessa team lead Ragavan Thurairatnam, where a Block intern plays The Guessing Game with the model, having it guess the everyday items she\u2019s thinking of. It\u2019s kind of funny that Dessa inadvertently spoils things by immediately guessing the object on the first try, twice in a row. It\u2019s even funnier when it shows some of the typical limitations of AI comprehension skills by carrying on with guessing after being told it won. But what stands out most is just how uncannily human Dessa\u2019s voice does sound.<\/p>\n