Fish Audio 发布 Live 3：全双工语音模型，响应延迟最低 186 ms
Fish Audio Releases Live 3, a Full-Duplex Voice Model That Reacts in 186 ms
语音 Agent 开发者可以看看这个。Fish Audio 的 Live 3 能边说边听，186 ms 的反应速度已经接近真人对话节奏，还分得清“嗯嗯”和真的想插话，这比很多半双工语音方案自然多了。做客服机器人或语音助理的值得跑个 demo 试试，不过暂时只有英语。
Fish Audio 发布 Live 3，一款面向语音智能体的全双工语音模型，核心指标是反应延迟最低 186 ms。与半双工模型“说完才能听”不同，Live 3 在说话的同时持续监听，支持边说边听的实时交互。
Live 3 在语义层面区分“嗯嗯”“好的”这类附和反馈与真正的打断：用户随口应和时它继续讲下去，用户确实要插话时才停下并切换话题。这种反馈识别与打断处理是其全双工能力的具体体现。
目前 Live 3 仅支持英语，主要面向构建语音 Agent 的开发者，用于客服、语音助理等需要低延迟自然对话的场景。
Fish Audio Releases Live 3, a Full-Duplex Voice Model That Reacts in 186 ms
Fish Audio released Live 3, a full-duplex voice model for voice agents. It listens while it speaks, separates “mm-hmm” from real interruptions, and can react in as little as 186 ms. English only at launch The post Fish Audio Releases Live 3, a Full-Duplex Voice Model That Reacts in 186 ms appeared first on MarkTechPost .
This report is categorized under AITOP's "Models" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Fish Audio, Live 3, 语音模型, 智能体.
Primary source verification: published directly by marktechpost with first-party authority.
