🗣️ AI Voice Cloner (XTTS v2)

A Streamlit web app for cloning voices using Coqui TTS.
Supports uploading, recording, or selecting reference voices and generating natural-sounding speech in multiple languages.

---

🚀 Features

• 🎤 Record voice directly in the browser
• 📤 Upload reference voice samples (WAV, MP3, M4A, OGG, FLAC)
• 🎵 Save and reuse voices from a gallery
• 🌎 Multilingual support (English, Spanish, French, German, Chinese, Japanese, etc.)
• 🎭 Control speech style, speed, and emotion
• 📂 Keep track of recent generations with playback & downloads
• 📥 Export audio as WAV or MP3

---

🛠 Tech Stack

Frontend / UI

• Streamlit: Web interface for interaction and real-time updates
• streamlit-option-menu: Sidebar navigation with a clean UI

Backend / Logic

• Coqui TTS (XTTS v2): Voice cloning & text-to-speech model
• pydub: Audio file conversion (WebM/MP3 ↔ WAV)
• librosa & soundfile: Audio signal processing
• NumPy: Array and numerical operations

Utilities

• requests: API calls (if extending functionality)
• python-dotenv: Manage secrets/API keys
• ffmpeg (system dependency): Required for audio encoding/decoding

Environment

• requests: API calls (if extending functionality)
• Virtual Environment (venv/) for dependency isolation

---

📂 Project Structure

voice_clone_app/
│
├── outputs/                  # Generated outputs (auto-created)
│   └── xtts_*.wav            # Generated files
│
├── voices/                   # Reference voices (auto-created)
│   ├── ref_*.wav             # Uploaded/recorded samples
│
├── app.py                    # Main Streamlit application
├── run_app.py                # Launcher (cross-platform, auto-opens browser)
├── test.py                   # Experimental/testing script
├── requirements.txt          # Python dependencies
├── LICENSE                   # Open-source license
├── .gitignore                # Ignored files/folders
└── README.md                 # Project documentation

---

⚙️ Installation

1. Clone the Repository

git clone https://github.com/EbrahimAR/AI-Voice-Cloner-XTTS-v2.git
cd AI-Voice-Cloner-XTTS-v2

2. Create virtual environment

python -m venv .venv
source .venv/bin/activate    # On Linux/Mac
.venv\Scripts\activate       # On Windows

3. Install dependencies

pip install -r requirements.txt

4. Install system dependencies

• ffmpeg is required for MP3 conversion:
  • Windows: choco install ffmpeg
  • macOS: brew install ffmpeg
  • Linux: sudo apt-get install ffmpeg

---

▶️ Run the app

streamlit run app.py

Or use the helper script:

python run_app.py

App will open at: http://localhost:8502

---

👨‍💻 Author

Ebrahim Abdul Raoof

LinkedIn

GitHub

---

📜 License

This project is licensed under the MIT License. See LICENSE for details.