voice / README.md
rahulrana0001's picture
feat: unify React Dubbing Studio UI with Gradio Manga AI in single Docker container
337d4b1
---
title: Maya Immersive Tamil Manga AI
emoji: πŸ—£οΈ
colorFrom: indigo
colorTo: purple
sdk: docker
pinned: false
---
# πŸ—£οΈ Multilingual Tamil TTS & Comic Reader AI
An optimized text-to-speech pipeline specifically designed for low-memory hardware (8GB RAM).
## πŸš€ Features
- **πŸ“– Comic Reader Mode**: Render PDF comic pages as images and read speech bubbles aloud.
- **🎭 Expressive Voices**: Multiple voice tones (Seductive, Excited, Dramatic) using Edge TTS.
- **πŸ“„ Document Support**: Extracts text from PDF, DOCX, and TXT files.
- **🧠 Hybrid Pipeline**: Uses Cloud APIs for TTS and Translation to save local RAM.
- **βš™οΈ Optimized OCR**: HD quadrant scanning for accurate text detection in comics.
## πŸ› οΈ Installation
1. Install Python 3.10+
2. Clone the repository: `git clone https://github.com/Rahul-new/voice.git`
3. Install dependencies: `pip install -r requirements.txt`
4. Run the app: `python app.py`
## 🎨 Voice Styles
- **Cheerful (Maya)**
- **Soft & Seductive (Maya)**
- **Excited & High-Pitch (Maya)**
- **Deep & Sensual (Sita)**
- **Dramatic Narrator (Sita)**