README.md

metadata

title: MSA model Multilingual TTS - Arabic & English
emoji: 🗣️
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 5.44.1
app_file: app.py
pinned: false
license: mit

MSA Model Multilingual TTS - Arabic & English

Generate high-quality speech from text with reference audio styling for Arabic and English languages.

Features

• Arabic & English Support: High-quality TTS for both languages
• Voice Cloning: Upload reference audio to clone voice characteristics
• Speed Control: Adjust speech speed from 0.5x to 2.0x
• Exaggeration Control: Fine-tune speech expressiveness
• Temperature Control: Control randomness in generation
• CFG/Pace Control: Adjust generation guidance

Usage

1. Select your language (Arabic or English)
2. Enter the text you want to synthesize
3. Optionally upload a reference audio file to clone a voice
4. Adjust the parameters as needed
5. Click "Generate" to create your audio