Whether you’re a content creator, developer, or audio enthusiast, this tool equips you with intuitive features to push the boundaries of voice transformation.
Key Updates and Features
- Support for Gradio 5.x and yt-dlp: Enjoy an improved web interface and enhanced YouTube video downloading capabilities.
- AI-Cover Support: Modify voices freely with ease. Download voice models (e.g., from Discord's AI Hub) and create realistic voice synthesis or AI covers.
---
Core Capabilities
1. Speech Recognition, Translation, and Text-to-Speech:
- Leverages OpenAI-Whisper, Faster-Whisper, and Whisper-Timestamped for seamless speech-to-text conversion.
- Supports Multi-Language translation and text-to-speech (TTS) via Google Translator and Edge-TTS.
2. Zero-Shot Voice Cloning:
- Generate realistic voices using E2 & F5-TTS engines. - With just 15 seconds of sample audio, you can unlock incredible voice replication capabilities.
- Includes 50+ celebrity voice models for rapid cloning.
3. Hassle-Free Installation:
- One-click setup via a simple Windows batch file. It’s fully portable and easy to remove.---
Demo Videos
- Getting Started Tutorial: [YouTube](https://youtu.be/z8g8LMhoh_o)
- Podcast Creation Demo: [YouTube](https://youtu.be/Wfo7vQCD4no)
- Multilingual Dubbing Examples: Check out examples that highlight our multilingual dubbing capabilities (supports over 100 languages):
- Original Content: [YouTube](https://youtu.be/ZtyhrZHbW0Y)
- English Dubbing: [YouTube](https://youtu.be/CA4WYdkJrkQ)
- Spanish Dubbing: [YouTube](https://youtu.be/hSEe0trPtnQ)
- Chinese Dubbing: [YouTube](https://youtu.be/qwExW2sReNc)
---
Why Choose Voice-Pro?
Voice-Pro offers a powerful yet user-friendly solution for voice manipulation. It’s designed to unlock creative possibilities for content creators, developers, and curious innovators experimenting with voice technology.
GitHub: Learn more and download here: [Voice-Pro GitHub](https://github.com/abus-aikorea/voice-pro)
---
previous post: https://news.ycombinator.com/item?id=42261909