---
format: "aidr-story-markdown/v1"
id: "48bed84d2ca4896ae358d6d622f3395bd7f6efd225732f7251e90e2429a7d637"
canonical_url: "https://aidr.today/48bed84d?lang=en"
title: "Fish Audio Releases Live 3, a Full-Duplex Voice Model That Reacts in 186 ms"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-11T04:43:53.000Z"
category: "Models"
topics: ["agent"]
source_urls: ["https://www.marktechpost.com/2026/11/10/fish-audio-live-3-full-duplex-voice-model/"]
summary: "Fish Audio released Live 3, a full-duplex voice model for voice agents that listens while speaking, distinguishes real interruptions from acknowledgments, and can react in as little as 186 ms. The model is English-only at launch."
---

# Fish Audio Releases Live 3, a Full\-Duplex Voice Model That Reacts in 186 ms

> [Open the canonical story](<https://aidr.today/48bed84d?lang=en>)

**Published:** 2026-11-11T04:43:53.000Z
**Category:** Models
**Topics:** agent

## Summary

Fish Audio released Live 3, a full\-duplex voice model for voice agents that listens while speaking, distinguishes real interruptions from acknowledgments, and can react in as little as 186 ms\. The model is English\-only at launch\.

## Sources

- [Story source](<https://www.marktechpost.com/2026/11/10/fish-audio-live-3-full-duplex-voice-model/>)