techcrunch.com/2026/10/24/blocks-new-voice-model-sounds-eerily-human Block’s new voice model sounds eerily human
Block, led by Jack Dorsey, unveiled Dessa, a full-duplex voice model from its research lab that runs locally and conveys laughs, pauses and emotion. It was trained solely on human speech and one NVIDIA GPU, and while not publicly available, Block is seeking safety researchers to test it.
— via TechCrunch, Ivan Mehta