Qwen3 TTS Voice Clone Studio - One Click Windows Installer

Bring your AI voice projects to life effortlessly with the latest Qwen3 TTS models — a cutting-edge advancement in text-to-speech and voice cloning technology. The new Qwen3 TTS models deliver exceptional clarity, natural prosody, and lightning-fast inference speeds optimized for both real-time applications and high-quality voice generation.
One of the best ways to run the Qwen3 TTS models locally is through the open-source FranckyB/Voice-Clone-Studio repository. This project provides a Gradio-based user interface, allowing you to test, tweak, and generate speech directly on your desktop. It also supports the Vibe Voice model from Microsoft.
To make this even easier, my one-click installer automates the entire process — it sets up the environment, installs dependencies, clones the necessary repositories, and downloads models automatically. It also comes prepackaged with Flash Attention for NVIDIA GPUs.
GitHub Repository: https://github.com/FranckyB/Voice-Clone-Studio
 
What's Included
Full automated environment setup — dependency installs, repo clones, and model downloads
Preconfigured scripts for launching the Voice Clone Studio project via Gradio UI
NVIDIA CUDA-accelerated Flash Attention extensions for enhanced performance
 
System Requirements
Windows OS
NVIDIA GPU with CUDA support (RTX 30XX or later preferred)
Minimum VRAM: 4 GB (more recommended for faster speeds)
Free Disk Space: At least 40 GB
Internet connection for dependencies and repository cloning
FFmpeg: https://www.ffmpeg.org/download.html
SOX (Sound eXchange): https://sourceforge.net/projects/sox/files/sox/
Rust (rustc) is now required for DeepFilterNet: https://rustup.rs/
Flash Attention 2 Windows Wheels: GitHub Releases
 
Usage Notes
Download and place the installer files in a dedicated folder. Double-click to install — no extra setup required.
Use the launch.bat file in the Voice-Clone-Studio folder to open the UI.
Use preset voices packaged with Qwen3 TTS under the Voice Preset tab.
For custom voice cloning, go to the Prep Samples tab: upload your audio file, transcribe it using Whisper or VibeVoice ASR, save your sample, then return to the Voice Clone tab to generate speech with your cloned voice.