Tyger: Open-Source Speech Decision Model Enables Full-Duplex Voice Agents

NineNineSix has open-sourced Tyger, a speech decision model that enables full-duplex voice agents capable of listening while speaking, handling interruptions, and responding with just 80ms decision latency on a single GPU.

2026-10-18 ~ 2026-10-18 · 3 related posts

• Open-weight TYGER speech decision model makes 80ms turn-taking calls for full-duplex voice agents — solyarisoftware · 2026-10-18
• Open-source Tyger-S2S voice agent runs natural, interruptible conversations on a single GPU — solyarisoftware · 2026-10-18
• Tyger brings full-duplex listening to voice agents that otherwise act like walkie-talkies — solyarisoftware · 2026-10-18