Marktechpost (@Marktechpost)T2·Models
78 pts
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.