README.md

metadata

title: BlueTTSV3 - Multilingual text-to-speech With VC
emoji: 🔊
colorFrom: blue
colorTo: indigo
sdk: gradio
sdk_version: 6.20.0
app_file: app.py
pinned: false
python_version: '3.12'

BlueTTSV3 — Multilingual text-to-speech With VC

This Space: https://huggingface.co/spaces/notmax123/BlueV3

Interactive demo for BlueTTS: fast on-device synthesis with ONNX Runtime. Type text, pick a language and voice, and generate audio in the browser. Project site: lightbluetts.com.

This Space was duplicated from thewh1teagle/lightblue-tts-hebrew and adapted for the current BlueTTS ONNX bundle.

Languages

• English, Spanish, German, Italian — phonemization with espeak-ng (via phonemizer), aligned with the multilingual tokenizer in the app.
• Hebrew — grapheme-to-phoneme via Renikud (ONNX).

Voices

Two built-in speaker styles (pre-extracted style JSON):

Voice	File
Roi	voices/Roi.json
Rotem	voices/Rotem.json

Implementation note

This Space runs inference from app.py (vocabulary, phonemization, ONNX sessions). It does not install the upstream blue Python package from GitHub (that package name replaced the old lightblue-onnx wheel and would conflict with pip’s expected name in a flat requirements.txt).

Model weights

ONNX checkpoints are not stored in this Space repo (file-size limits). On first startup, download_models.py fetches them from the public model repo notmax123/BlueV3-onnx into ./onnx_slim/ (see ONNX_DIR in app.py).

Training / finetuning / voice-export weights (PyTorch / Safetensors): notmax123/blue.

If you fork this Space and point downloads at a private repo, set a Hugging Face write token as the Space secret HF_TOKEN so authenticated downloads still work.

Links

• This demo (Space): huggingface.co/spaces/notmax123/BlueV3
• ONNX weights: notmax123/BlueV3-onnx
• PyTorch / training weights: notmax123/blue
• Source code: maxmelichov/BlueTTS on GitHub
• Hebrew G2P: thewh1teagle/renikud

Local development

Dependencies are listed in requirements.txt. With Python 3.12:

pip install -r requirements.txt
python download_models.py   # once, to populate onnx_slim/
python app.py               # or: gradio will launch from app_file when run by HF

To refresh requirements.txt from uv:

uv export --no-hashes --no-emit-project > requirements.txt

License

See the BlueTTS repository and the BlueV3-onnx model card for licensing of code and weights.