<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Speech Model on LexxWire — US Tech &amp; AI News Daily</title><link>https://blog.lexx.in/tags/speech-model/</link><description>Recent content in Speech Model on LexxWire — US Tech &amp; AI News Daily</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sun, 25 Oct 2026 17:59:32 -0400</lastBuildDate><atom:link href="https://blog.lexx.in/tags/speech-model/index.xml" rel="self" type="application/rss+xml"/><item><title>Block's Dessa: The Voice AI That Learned to Talk From Speech Alone</title><link>https://blog.lexx.in/webstories/block-dessa-voice-ai-speech-only-webstory/</link><pubDate>Sun, 25 Oct 2026 17:59:32 -0400</pubDate><guid>https://blog.lexx.in/webstories/block-dessa-voice-ai-speech-only-webstory/</guid><description>Block&amp;#39;s research lab unveiled Dessa, a full-duplex voice AI it says was trained only on human speech — it listens while it talks, hears emotion and laughter, and runs locally on a laptop.</description></item><item><title>Block's Dessa Voice AI Learned to Talk From Speech Alone — and It Sounds Human</title><link>https://blog.lexx.in/news/block-dessa-voice-ai-human-speech-oct-2026/</link><pubDate>Sun, 25 Oct 2026 15:58:00 -0400</pubDate><guid>https://blog.lexx.in/news/block-dessa-voice-ai-human-speech-oct-2026/</guid><description>Block&amp;#39;s Dessa voice AI learned to talk from human speech alone — no text, no pretrained models. It runs on a MacBook and sounds unsettlingly human.</description></item></channel></rss>