Voice Creator Pro 1.3.11
 

AI Voices That Sound Natural. The most human-sounding voice AI. Clone any voice with 3 seconds of audio, or describe your perfect voice and bring it to life. All-in-one human-sounding local AI voice generator. Voice cloning, voice design, text-to-speech, and speech-to-text, with full REST API access.
Everything You Need
Professional voice AI tools, running entirely on your machine.
Hyper-Realistic Voice AI
State of the art technology that can clone a voice with 3s of audio or generate realistic voices from description.
Unlimited Everything
No limits on generations, characters, or usage. Create as much content as you want.
10 Languages Supported
Clone voices in English, Chinese, Japanese, Korean, German, French, Spanish, Russian, Italian and Portuguese.
Full API Access
Integrate voice cloning into your own apps and workflows with a complete local REST API.
Secure Voice Cloning
All processing happens locally on your device. Your voice data never leaves your computer.
Commercial Use
Full commercial use allowed. Use cloned voices in your videos, podcasts, and products.
Release NotesAdded
- Multi-model support - seamlessly switch between Qwen3 and Chatterbox TTS models
- The Chatterbox lower quality turbo model supports tags like[chuckle] and[cough]
- 48 kHz HQ audio mode. Enables higher quality generations.
- Mobile-responsive UI - header, generate, output, and history sections adapt to narrow screens
Fixed
- Multi-model fallback: mode support checks removed from API endpoints; model_loader auto-selects a compatible model
- Speaker and language lookups fall back to alternative providers when active model doesn't support them
- "Auto" language option always appears in dropdown regardless of model
System Requirements
- OS: Windows 10 version 17763.0 or higher
- Memory: 4 GB = (Minimum), 8 GB (Recommended)
- Video Memory: 6 GB