Fish Audio Releases Live 3 Full-Duplex Voice Model
Fish Audio released Live 3, a full-duplex voice model that internalizes turn-taking into the speech model itself, learning from real human conversations when to acknowledge, wait, respond or stop instead of relying on silence thresholds and hand-written rules. Fish Audio claims reactions as fast as 186 ms for short cues, but the launch is English-only with no published benchmark scores. It is available via the Fish Agent Platform, API and on-prem for enterprises at $0.035/min through the end of 2026.
Full Report
▲ Marktechpost AI · 2026-11-11 04
▲ Fish Audio just released Live 3, a full-duplex voice model that keeps listening while it speaks, so voice agents stop talking over callers.
The key idea is moving turn-taking into the speech model itself. Instead of silence thresholds and hand-written rules, Live 3 was trained on real human conversations. It learns when to acknowledge, wait, respond or stop, so "yeah" lets it keep going while "wait, actually" makes it yield.
Fish Audio says Live 3 can decide to react in as little as 186 ms for short cues like "mm-hmm" or "okay, 415". For context, Eleven Realtime v1 Max reports 0.57 s average time to first audio, a different measurement. It is a trade-off though: Live 3 is English only at launch, and Fish Audio has published 0 benchmark scores so far.
It runs on the Fish Agent Platform, the Fish Audio API and on-prem for enterprises. Agents are 0.07 list), covering STT, TTS and basic LLMs......
Full analysis:
