higurashi-ai/Haru

Haru: a low-latency, multilingual, full-duplex spoken dialogue model

Open original source ↗

From the publisher

README & documentation

Source preview

Read the project’s overview, installation instructions and usage examples. The original README is the source of truth.

Model · Technical blog · Technical blog (Japanese) 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. the user's audio and produces one frame of its own audio and text. User audio, model audio and model text are summed into a single position of the language model, so listening and speaking never wait for each other. per frame. A small MLP head with MeanFlow sampling produces it in one step from the language model's hidden state; there is no separate audio transformer and there are no discrete audio tokens. reference clip sets the voice. Japanese, Russian and Korean. hold a padding token, and an end-of-padding token on the frame before the model starts to…

higurashi-ai/Haru on GitHub A short preview, not the full document.

Read the full README ↗ · Preview checked 2026-11-15T12:40:38.289Z

Inside the original README — Document outline
  1. Haru
  2. How it works
  3. Repository
  4. Quick start
  5. Python
  6. The system prompt
  7. Offline
  8. Serving with vLLM-Omni
  9. Custom kernels
  10. Limitations
  11. License
  12. Acknowledgments

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the README

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

What this repository does

Haru: a low-latency, multilingual, full-duplex spoken dialogue model

Repository facts

Owner
higurashi-ai
Primary language
Python
Stars
380
Forks
26
Open issues + pull requests
2
License
Apache-2.0
Archived
No
Default branch
main
Created
2026-11-12T11:15:42.000Z
Last push
2026-11-13T06:21:17.000Z

Topics and intended use

No topics were included in the latest source metadata.

Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.

Evaluate before installing

Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.

README and project files

Issues and maintenance discussion

Releases and changelog

Source and freshness

Source: GitHub. Metadata observed 2026-11-15T12:25:38.091Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related repositories

public-apis/public-apis

EbookFoundation/free-programming-books

donnemartin/system-design-primer

vinta/awesome-python

practical-tutorials/project-based-learning

NousResearch/hermes-agent