Voice Soundboard

About

Voice Soundboard is a comprehensive Python library designed to transform text into natural-sounding speech, ideal for AI agents and developers. It provides a robust Python API, a command-line interface, and seamless integration as an MCP server, offering over 40 tools for AI agents like Claude. Leveraging the Kokoro TTS engine, the library supports multi-voice synthesis with 54+ voices, 19 emotions, natural language style control, real-time streaming, and advanced features such as SSML support, zero-shot voice cloning, and multi-speaker dialogue for highly expressive audio generation.

Key Features

• Zero-shot voice cloning from 3-10 second audio samples
• Multi-voice synthesis with 54+ voices, 19 emotions, and natural language style control
• Real-time streaming and SSML support for fine-grained speech control
• Paralinguistic tags (e.g., [laugh], [sigh]) and support for 23 languages
• 0 GitHub stars
• Integration as an MCP server, providing 40+ tools for AI agents

Use Cases

• Empowering AI agents and chatbots with natural and expressive speech capabilities
• Integrating advanced text-to-speech functionality into Python applications and scripts
• Generating professional voiceovers, podcasts, and audiobooks for content creators