Fish Audio · Full-Duplex Voice
Live 3
Fish Audio has released Live 3, a full-duplex voice model for voice agents. It can listen while it speaks, distinguish backchannel cues such as "mm-hmm" from real interruptions, and react in as little as 186 ms. It is English only at launch.
Open the source ↗Similar Audio & Speech releases
- Duo: A Reciprocal World Model for Full-Duplex Interaction
inclusionAI (Hengyuan Cao, Biao Gong, Guoshan Lu, Qiyuan Zhang, Lin Liu, Yiding Tian, Yilei Jiang, Yuxin Ma) · Full-Duplex World Model · Week 47, 2026
- Sophon-Realtime v1
Adventists AI · Full-Duplex Voice · Week 47, 2026
- Muse Realtime Voice and Muse Realtime Avatar
Meta · Realtime voice avatars · Week 46, 2026
- MOSS-Live
模思智能 (MOSS) · Full-duplex voice agent · Week 46, 2026
- Dessa
Block (Dessa research lab) · Speech-only conversation model · Week 45, 2026
- Eleven v4 and v4 Turbo
ElevenLabs · Expressive TTS Model · Week 41, 2026
More from Fish Audio
- Fish Audio Drama 3
Fish Audio · Directable TTS · Week 43, 2026
- Fish Audio S2 (Open Source)
Fish Audio · Text-to-Speech · Week 11, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.