Voice Replication with Coqui XTTS

Generate a synthetic voice using Coqui TTS XTTS, based on a real voice recording.

Features

• Uses Coqui's XTTS multilingual model
• Clone your voice from a single .wav clip
• Outputs high-quality speech in .wav format

Getting Started

1. Clone the repository

git clone https://github.com/christalphilip/voice-replication.git
cd voice-replication

2. Install dependencies

pip install -r requirements.txt

Usage

1. Record a clear voice clip (real_recording.wav)
2. Edit the text variable in voice_replication.py
3. Run the script:

   python mood-music.py

The generated audio will be saved as synthetic_recording.wav.

Example Output

Input: real_recording.wav Text: "Hello, this is a synthetic voice created from an audio recording of Christal's voice." Output: synthetic_recording.wav

Project Structure

voice-replication/ ├── voice_replication.py
├── requirements.txt
├── README.md
├── LICENSE
├── .gitignore
└── example_outputs/ ├── real_recording.wav
└── synthetic_recording.wav

License

This project is licensed under the MIT License.