Downloads · 30 days
0
notmax123/blue-onnx
blue-onnx is a text-to-speech model from notmax123. Use it when you need text read aloud. The card lists the license as mit.
This repository is the ONNX model bundle for BlueTTS: fast Hebrew-first multilingual speech synthesis with ONNX Runtime and optional NVIDIA TensorRT engines (see the GitHub repo).
Downloads · 30 days
0
Access
Public
Updated Apr 24, 2026
Repo size
2.2 GB
Likes
3
Public
Click a slice to open those files.
.json672 MB · 71%
From the Hugging Face model README
This repository is the ONNX model bundle for BlueTTS: fast Hebrew-first multilingual speech synthesis with ONNX Runtime and optional NVIDIA TensorRT engines (see the GitHub repo).
Project home (install, usage, examples, TensorRT): https://github.com/maxmelichov/BlueTTS
Try in the browser: Hugging Face Space — notmax123/Blue · Website: lightbluetts.com
BlueTTS targets native Hebrew quality (including nikud and disambiguation of common homographs) while staying fast enough for real-time and batch use. The reference codebase also supports English, Spanish, Italian, German, and mixed-language segments in one utterance.
Hebrew G2P at inference uses the renikud ONNX model (model.onnx); download it separately (see below).
| Repo | Purpose |
|---|---|
This repo (notmax123/blue-onnx) | ONNX checkpoints for BlueTTS inference |
notmax123/blue | PyTorch / Safetensors weights and stats for training, finetuning, and exporting new voice JSON |
Repo id is case-sensitive: notmax123/blue-onnx.
hf download notmax123/blue-onnx --repo-type model --local-dir ./onnx_models
wget -O model.onnx https://huggingface.co/thewh1teagle/renikud/resolve/main/model.onnx
Classic CLI equivalent:
huggingface-cli download notmax123/blue-onnx --repo-type model --local-dir ./onnx_models
Clone BlueTTS, run uv sync, place the ONNX bundle and model.onnx as in the project README, then use src.blue_onnx.BlueTTS or the examples/ scripts.
Minimal pattern:
import soundfile as sf
from src.blue_onnx import BlueTTS
tts = BlueTTS(
onnx_dir="onnx_models",
style_json="voices/female1.json",
renikud_path="model.onnx",
)
samples, sr = tts.synthesize("Hello, this is a short English sample from BlueTTS.", lang="en")
sf.write("output.wav", samples, sr)
(Adjust PYTHONPATH / imports if you install the package instead of running from a clone.)
Reported reference throughput on tuned setups (see project materials and lightbluetts.com); your hardware, batching, and TensorRT vs ONNX Runtime settings will change these numbers.
| Hardware | Approx. speed | ~1 h audio |
|---|---|---|
| NVIDIA RTX 3090 (GPU) | very high RTF | on the order of seconds |
| Typical CPU | strong RTF | on the order of minutes |
| Apple M1 class | strong RTF | on the order of a few minutes |
BibTeX and paper links are maintained in the BlueTTS README.
MIT — see the BlueTTS repository.