Inworld AI Blog· Inworld AI·· 2026-05-14PickAI score49
Inworld pairs Realtime TTS-2 with Stream Vision Agents for a realtime voice agent that can see and listen
Realtime voice agents can now see, listen, and engage
AI summary
Inworld teamed up with Stream to build a reference implementation, Crashout Buddy, combining the latest speech model Realtime TTS-2 with Stream's open-source Vision Agents framework, so it can see facial expressions, hear speech and adjust its delivery in real time.
Why it matters
The post shows how to turn visual signals and emotional context into speech delivery instructions, which readers can use to judge whether this realtime voice pipeline can be plugged into their own projects.
Source: Inworld AI Blog · inworld.ai