{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"The Daily AI Chat","title":"Block's Dessa Voice Model Sounds Eerily Human","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/26cef536\"></iframe>","width":"100%","height":180,"duration":1154,"description":"Block has demonstrated Dessa, a research voice model designed for natural, two-way conversation. It can listen while speaking and produce expressive pauses, laughter, and other speech cues. The company says it trained the model using speech on a single NVIDIA GPU rack and that it can run locally on a MacBook M4 Max or better.","thumbnail_url":"https://img.transistorcdn.com/VAqhAsoxSwBsu4aV2JnmHv92a42NrJ0Mn3its5WBdng/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS84Njcw/NDFmOGNkYzM0NjQ0/YWE4NjU1OGMwZWE2/ZGE5YS5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}