AllVoiceLab

关于

The AllVoiceLab Model Context Protocol (MCP) server facilitates interaction with powerful text-to-speech and video translation APIs, enabling MCP clients like Claude Desktop and Cursor to generate speech, translate videos, and perform intelligent voice conversion. It serves scenarios such as short drama localization for global markets, AI-Generated audiobooks, and AI-Powered film/TV narration production. The server utilizes multi-engine technology to unlock infinite possibilities for voice, including natural voice generation in 30+ languages, real-time voice conversion, vocal separation, multilingual dubbing, speech-to-text, subtitle removal, and voice cloning.

主要功能

• Text-to-speech conversion in 30+ languages
• Real-time voice conversion
• Vocal separation
• Multilingual video translation and dubbing
• Voice cloning
• 22 GitHub stars

使用案例

• Short drama localization for global markets
• AI-generated audiobooks
• AI-powered film/TV narration production