<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Realtime on Best of AI</title><link>https://bestofai.io/tags/realtime/</link><description>Recent content in Realtime on Best of AI</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Sat, 03 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://bestofai.io/tags/realtime/index.xml" rel="self" type="application/rss+xml"/><item><title>Eleven v4</title><link>https://bestofai.io/models/eleven-v4/</link><pubDate>Sat, 03 Oct 2026 00:00:00 +0000</pubDate><guid>https://bestofai.io/models/eleven-v4/</guid><description>&lt;p&gt;ElevenLabs launched Eleven v4 on September 28, 2026, improving expressiveness and voice cloning (down to a 10-second sample) across more than 90 languages. Eleven v4 Turbo is the same model tuned for real-time use, running at roughly 100 milliseconds of median latency. Eleven v4 ranked first on the Artificial Analysis Provider Voice Arena leaderboard for September 2026, with about 75% of listeners preferring it over five rival services in blind tests.&lt;/p&gt;</description></item><item><title>Qwen-Audio-3.1-Realtime</title><link>https://bestofai.io/models/qwen-audio-3-1-realtime/</link><pubDate>Sat, 03 Oct 2026 00:00:00 +0000</pubDate><guid>https://bestofai.io/models/qwen-audio-3-1-realtime/</guid><description>&lt;p&gt;Alibaba released Qwen-Audio-3.1-Realtime on September 28, 2026 as the flagship of a five-model Qwen-Audio-3.1 stack that also covers speech recognition and text-to-speech. It&amp;rsquo;s built for full-duplex voice agents, meaning it can listen and respond at the same time and decide mid-conversation when to speak versus when to call an external tool.&lt;/p&gt;</description></item></channel></rss>