Instantly clone any voice with a 10-20 second sample. Powered by Coqui XTTS v2 and Groq Llama 3.1 for emotional, high-fidelity speech synthesis.
Ultra-Fast Scripting
Auto-generate narrations via Groq.
0.75x Speed Control
Optimized for natural clarity.
| Component | Technology |
|---|---|
| Voice Engine | XTTS v2 (Replicate) |
| Logic | Python / Streamlit |
| Database | JSON Local Persistence |
// Quick Start Guide
$ git clone https://github.com/PRAJWALJAN4/voice-cloning-lab.git
$ pip install -r requirements.txt
// Configure .env with:
REPLICATE_API_TOKEN=******
GROQ_API_KEY=******