Haru
Haru: a low-latency, multilingual, full-duplex spoken dialogue model
Haru launched on 12 November 2026. It ranked #57 on Daily Launch on 20 November 2026 with a Launch Score of 36, from 675 stars in 8 days on GitHub. It was new in the ranking that day.
What is Haru?
Haru is a low-latency and multilingual full-duplex spoken dialogue model: it listens and speaks at the same time, the way people do on a phone call. This repository contains the inference code for Haru-4B, a pretrained base model, with three implementations and a web demo.
From its README on GitHub
Haru is a repo by higurashi-ai on GitHub. It is written in Python and released under the Apache-2.0 license.
How to get Haru
Get it from its repository on GitHub.
Launch timeline
Launch Score, last 7 days
Ranked on one day so far: 36 of 100 on 20 November.
#136 of 226 in the roundup for the week of 16-22 November 2026.