higurashi-ai/Haru
Model
Can I trust it?
Worth a closer look before you use it.
Warnings Check
Very new: it was created 5 days ago. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change 3 days ago.
Licence OK
Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
A low-latency, multilingual full-duplex spoken dialogue model that listens and speaks at the same time, operating on 133 ms frames at 7.5 Hz. Provides PyTorch, MLX (Apple silicon) and vLLM-Omni implementations plus a web demo, with character cards and reference voice clips for…
Who it's for
Developers and researchers building real-time voice assistants or spoken dialogue systems on NVIDIA GPUs or Apple silicon
How to use it
Install
pip install -e ./haruFrom its README. Check it there before running it.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up higurashi-ai/Haru in my project. Follow its README: https://github.com/higurashi-ai/Haru. Explain each step and check it is safe before running anything.
Star curve
On the radar
Its place among the radar's top 100, day by day, with #1 at the top. Gaps are days it was out of the top 100.
Records
- Best place on RepoAlerts: #32, on 14 Nov 2026
- In the top 100 for 2 days since 14 Nov 2026
Get alerts for repos like this
We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/higurashi-ai/Haru?ref=badge)Similar repos
- debpalash/VoiceStudio
Desktop application for local voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation, with a local API and MCP server for agents. Runs on NVIDIA CUDA, Apple Silico
- iiinno/OpenHinoVoice
A Windows app for Japanese voice input. Speech is recognized locally with speech.cpp; the text can optionally be cleaned up by ChatGPT, OpenCode Go or OpenAI. Press a hotkey to record, Enter to paste
- adventists-ai/sophon-realtime
Open full-duplex speech-to-speech voice model family that listens while the user talks, detects paralinguistic cues such as tone and emotion, and replies with synthesized speech that can include laugh
- zeekk0/OpenAmika
Live2D anime companion that talks with the user by voice and text in real time and keeps long-term memory of them. Runs on the user's own Windows PC, with the language model served through OpenRouter
- JMS1717/ming-voice
A fully local real-time speech-to-speech voice assistant that runs the Ming-3.0-audio-tiny model on AMD Radeon GPUs (and experimentally NVIDIA). It detects end of turn, answers aloud in about 0.23 s,
- runboubou/boubou
A command-line tool for talking with AI out loud. Runs open models locally on your machine, with microphone input, spoken replies, echo cancellation and speech detection. Also serves a browser or phon