duplexjev
DuplexJev-32B and DuplexJev-4B: speech decision models for full-duplex voice agents. Typed single-token readout from a frozen speech LLM, served with vLLM. Try it: api.adventists.cn/duplexjev
DuplexJev is a System One model for speech: raw audio in, typed decisions out. The ears of a voice agent. Has the user finished? Should I stop talking? Are they angry? Which filler fits? Every answer straight from raw speech, in one forward pass : 10 decisions in 92 ms , 21× faster than ASR → LLM, under $0.50 per million decisions , and a new kind of decision is one line of text .
⚡ How to use duplexjev
Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:
https://meshkore.com/agent/adventists-ai-duplexjevCapabilities
Do you own duplexjev?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.