We're excited to announce the launch of RBS Voice Cloner v1.0.0 — a free, fully offline AI voice cloning tool for Windows. Clone any voice from a short audio sample and generate natural-sounding speech in 28+ languages, all running locally on your PC.
What is RBS Voice Cloner?
RBS Voice Cloner is powered by the XTTS v2 AI engine — one of the most realistic open-source text-to-speech models available. It lets you:
- Clone a voice from just a 5–30 second audio sample
- Generate speech in English, Hindi, Spanish, French, German, Japanese, Chinese, and 20+ more languages
- Record directly from your microphone or upload any audio file
- Edit audio with the built-in waveform editor (trim, noise reduction, fade)
- Export as WAV or MP3
- Run GPU-accelerated on NVIDIA CUDA or fall back to CPU automatically
100% Free and Offline
After the first launch — which downloads the ~2 GB XTTS v2 model from Hugging Face — the app runs entirely offline. No subscription, no cloud processing, no data sent anywhere. Your voice samples and generated audio stay on your machine.
System Requirements
- Windows 10 or Windows 11 (64-bit)
- 8 GB RAM minimum (16 GB recommended)
- 4 GB+ free disk space
- Internet connection for first-time model download only
- NVIDIA GPU recommended for fast generation (CPU works but is slower)
Responsible Use
Voice cloning is powerful technology. Please only clone voices you have permission to use — your own voice or voices where you have explicit consent. Never use this tool to impersonate others or create misleading content.