Downloads · 30 days
0
hexa-tts-5b
Hexa09/hexa-tts-5b
hexa-tts-5b is a text-to-speech model from Hexa09. Use it when you need text read aloud. The card lists the license as apache-2.0.
Hexa TTS is a massive 5-billion parameter Text-to-Speech system designed for high-fidelity, emotional, and multi-speaker speech synthesis across 15 languages.
Access
Public
Updated Feb 4, 2026
Repo size
—
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pyc33.7 KB · 50%
At a glance
- Task
- Text-to-Speech
- License
- apache-2.0
- Access
- Public
- Created
- Feb 4, 2026
- Updated
- Feb 4, 2026
- SHA
- 7e9a7de8
Spaces
Model card
From the Hugging Face model README
Hexa TTS 5B
Hexa TTS is a massive 5-billion parameter Text-to-Speech system designed for high-fidelity, emotional, and multi-speaker speech synthesis across 15 languages.
Model Details
- Architecture: Transformer-based (Flow Matching / Autoregressive)
- Parameters: ~4.92 Billion
- Languages: 15 (English, Bangla, Chinese, Spanish, French, German, Japanese, Korean, Russian, Portuguese, Italian, Hindi, Arabic, Turkish, Dutch)
- Features: Emotion Control, Multi-Speaker embedding.
Usage
This repository contains the untrained model definition and configuration.
# Coming soon: AutoModel support
from src.hf_model import HexaModel
from src.config import HexaConfig
config = HexaConfig() # Defaults to 5B
model = HexaModel(config)
Training
To train this model, use the provided src/train_hf.py script on a multi-GPU cluster (A100/H100 recommended).
- Task
- Text-to-Speech
- License
- apache-2.0
- Languages
- en, bn, zh, es, fr, de
- Created
- Feb 4, 2026
- Updated
- Feb 4, 2026