Block research has announced Dessa, a full-duplex voice AI model trained directly on human speech rather than text pipelines.
Running locally on consumer hardware with an NVIDIA GPU, it supports simultaneous speaking and listening while incorporating natural vocal expressions.
How the new system works
The system's key difference is that it was trained exclusively on recordings of human speech, rather than text that is later converted to voice. According to the company, this allows it to sound unusually natural, including features such as pauses, laughter and crying.
The model has the ability to speak and listen simultaneously, meaning that the conversation can flow just like a normal conversation between two people. It was trained using only human speech and an NVIDIA graphics card, and its technical specifications allow it to run locally on high-performance everyday computers, such as systems with Apple M4 Max processors or newer.
Who has access?
The model is not currently available to the general public. Block has asked security experts to test it first to examine its capabilities and implications.
READ ALSO
OpenAI cuts off direct access to artificial intelligence models on the internet
Jack Dorsey and team member Ragavan Thurairatnam shared details and examples on social media. Block is in the financial services business and sells solutions to small businesses, with its Square service already using voice technology for ordering.
G
Hacks.gr on Google
Set it as a preferred source for cybersecurity updates.
Preferred source
Top comments (0)