Jev 判断语音会话里用户在跟哪个 agent 说话

kwindla @kwindla原推发布于 2026.10.04

在 X 上打开原推

I love this Jev + voice demo: Jev decides which of the two agents in the session the user is talking to. The Jev inference call adds about 100ms, so voice-to-voice latency here is still way under our target of 1,500ms P95. (This is using the very fast PhoneLLM model.) Jon's thread has another example of six "characters" in the session. Full code is in his thread, too. (It's worth noting that Claude and Codex can both one-shot complex Pipecat agents like this, now, getting all the low-level hard things like turn detection right, and using abstractions like workers to build sub-agents and handoff.)

这条是引用着另一条写的：「Opus 5.5 一次成型双角色语音机器人管线」