Fish Audio 发布全双工语音模型 Live 3
做语音智能体的朋友可以看看 Fish Audio 新出的 Live 3，能听懂"嗯嗯"这类反馈，也不会在用户话说一半时插嘴。相比传统串行语音助手，全双工让对话自然很多，企业还能免费申请定制，开发者可以直接上手试。
Fish Audio 推出全双工语音模型 Live 3，主打实时语音智能体场景。模型能在对话中给出"mm-hmm""ahan"等倾听反馈，理解被打断的情境，避免电话里常见的尴尬停顿和被中途打断的问题。
Live 3 的核心机制是全双工架构，即模型在同一时间既能听又能说，而不是传统语音助手的"听完再说"串行模式。这使得它可以实时判断用户是否说完、何时该插话、何时该保持沉默，从而支持更自然的对话节奏。
Fish Audio 表示企业客户可预约演示获取免费定制智能体，并承诺为前 1000 名提交用例的用户免费搭建方案。在竞争激烈的语音智能体赛道，全双工能力和倾听反馈是 Live 3 与传统语音助手的主要差异点。
Introducing Live 3: a full-duplex voice model built for real-time voice agents. No more awkward pauses on phone calls or getting interrupted mid-sentence by voice agents. It knows listening cues ("mm-hmm" and "ahan"), understands interruptions, and never cuts in between conversations. Use it here: s.fish.audio/yf7utj Rissa Cao @rissa_cao Introducing @FishAudio Live 3: a full-duplex voice model that listens, says "mm-hmm," and knows when to shut up. Enterprise? Book a demo for your free custom agent: s.fish.audio/vxhgs6 Reply with your use case - we'll build it free for the first 1,000 people.
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Fish Audio, Live 3, 语音智能体, 全双工语音.
Source attribution: curated from Fish Audio (@FishAudio).
