---
license: mit
language:
  - multilingual
tags:
  - text-to-speech
  - speech-synthesis
  - hebrew
pipeline_tag: text-to-speech
---

# Blue — PyTorch weights (training, finetuning & voice export)

This repository contains **Safetensors / PyTorch checkpoints** and **multilingual latent statistics** for **[BlueTTS](https://github.com/maxmelichov/BlueTTS)** — Hebrew-first multilingual text-to-speech with optional English, Spanish, Italian, German, and mixed-language synthesis in the reference code.

**Project home (install, ONNX inference, examples):** [https://github.com/maxmelichov/BlueTTS](https://github.com/maxmelichov/BlueTTS)

**Live ONNX demo (browser):** [Hugging Face Space — notmax123/Blue](https://huggingface.co/spaces/notmax123/Blue)

> **End-user synthesis:** Use the ONNX model bundle **[`notmax123/blue-onnx`](https://huggingface.co/notmax123/blue-onnx)** with the BlueTTS README. This **`notmax123/blue`** repo supplies **training / finetuning weights** and files needed to **export new voice style JSON** for ONNX; it is not the ONNX runtime bundle.

## Files

| File | Role |
|------|------|
| `blue_codec.safetensors` | Audio codec: mel ↔ latent, discrete/continuous conversion. |
| `stats_multilingual.pt` | Latent mean/std for normalization (same statistics as training). |
| `vf_estimator.safetensors` | Text-to-latent acoustic model (text encoder, reference encoder, flow-matching core). |
| `duration_predictor.safetensors` | Duration predictor checkpoint. |

## Download

Repo id is **case-sensitive** — use `notmax123/blue` (not `Blue`).

```bash
hf download notmax123/blue --repo-type model --local-dir ./pt_weights
```

Equivalent with the classic CLI:

```bash
huggingface-cli download notmax123/blue --repo-type model --local-dir ./pt_weights
```

## How to use

1. **Training or finetuning:** Follow the [training](https://github.com/maxmelichov/BlueTTS/tree/main/training) directory in the BlueTTS GitHub repository.

2. **New voices for ONNX inference:** Clone [BlueTTS](https://github.com/maxmelichov/BlueTTS), install with the `export` extra, download these weights locally, and run `scripts/export_new_voice.py` (see script docstring and project README).

## License

MIT — see the [BlueTTS repository](https://github.com/maxmelichov/BlueTTS) for the full license text.