Voice Soundboard

About

Voice Soundboard is a Python library that provides robust text-to-speech capabilities, wrapping the Kokoro TTS engine. It offers a flexible Python API, a command-line interface, and an MCP server, making it ideal for AI agent developers, Python application builders, and content creators. The library includes over 54 voices, 19 emotions, natural language style control, and advanced features such as zero-shot voice cloning and multi-speaker dialogue. It runs entirely locally, supporting real-time audio streaming and fine-grained control over speech output.

Key Features

• Multi-voice synthesis with 54+ voices and 19 emotional styles.
• Advanced speech control via SSML, natural language styles, and emotion blending.
• Integrates as an MCP server, exposing 40+ tools for AI agents like Claude.
• Real-time audio streaming and low-latency response for interactive applications.
• 0 GitHub stars
• Optional voice cloning from short audio samples and multi-speaker dialogue generation.

Use Cases

• Enabling AI agents to generate dynamic, expressive speech through the Model Context Protocol (MCP).
• Integrating comprehensive text-to-speech functionality into Python applications for various purposes.
• Creating high-quality voiceovers, podcasts, or audiobooks with diverse voices and emotional tones.