The story’s score and claims

Comments on No. 85 of 144 · higurashi Tech Blog · edition of Thursday 19 November 2026

Haru-4B: A voice AI that can listen and speak at the same time

Summary

Haru-4B is an open-weight pretrained base model, built on Qwen3.5-4B, that listens and speaks at the same time, learning turn-taking, backchannels, and interruptions from about 40 million hours of real, mostly unscripted speech rather than synthetic dialogue.

Comments

Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules