Reading the repo
Opening the box…
Reading the repo
Opening the box…
How to install on Windows
Haru: a low-latency, multilingual, full-duplex spoken dialogue model
GitHub didn't answer, so this is the saved copy from 1 days ago
Will it work on Windows?
With an NVIDIA GPU (about 12 GB of memory):
pip install -e ./haru
python -m haru.server --hf-repo higurashi-ai/Haru-4B
Open http://localhost:8998, pick a character, give the model a voice, and
talk. A browser only gives a page microphone access on localhost or over
HTTPS.
For low latency, we recommend wired headphones and a wired microphone. Bluetooth devices add 100 ms or more.
To let someone else try it, add --share (pip install -e "./haru[share]"): the
server prints a public HTTPS link that tunnels to it. Anyone with the link can
use the demo, and the traffic passes through Gradio's share servers.
Bring your own voice. Haru ships without voice clips. In the demo, upload
or record a clip of the voice the model should speak with: one speaker, 3
seconds to 3 minutes, clean speech. In Python, pass it as reference. Only
use voices you have the right to use.
To give the demo a default voice, save a clip as
haru/haru/assets/voices/<language>.flac (en.flac, ja.flac, ...) and
restart the server: the demo then offers it as the default voice of that
language. Without the file, the demo does not show the option.
On a Mac with Apple silicon, build the native app (see
haru_mlx/swift):
cd haru_mlx
python3 -m venv .venv && source .venv/bin/activate
pip install -e .
cd swift && ./build_app.sh # then open build/Haru.app
Then run powershell -ExecutionPolicy Bypass -File .\setup.ps1. It stops at the first error and is safe to run again. Servers and tests aren't started; it lists them at the end. Read it first.
Needs Git: winget install Git.Git
git clone https://github.com/higurashi-ai/Haru.git cd Haru
Python 3
winget install Python.Python.3.12
Run these in Git Bash (installed with Git) or WSL — not PowerShell. Do the README instructions above first.
pip install -e ./haru python -m haru.server --hf-repo higurashi-ai/Haru-4B python3 -m venv .venv && source .venv/bin/activate pip install -e . cd swift && ./build_app.sh # then open build/Haru.app
The steps run shell scripts (.sh). Use Git Bash (winget install Git.Git) or WSL2 (wsl --install).
No reports for Windows yet.
GitManual AI Agent reads the 5 key files and writes a step-by-step guide for Windows. Once written, it's saved for everyone.