advanced-tts-mcp

advanced-tts-mcp

3.2

If you are the rightful owner of advanced-tts-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

Advanced TTS MCP Server is a high-quality, feature-rich Text-to-Speech server implemented in TypeScript, designed for professional applications requiring natural, expressive speech synthesis with advanced controls and zero external dependencies.

The Advanced TTS MCP Server is a sophisticated Text-to-Speech solution that offers a wide range of features for creating natural and expressive speech. Built with a native TypeScript implementation, this server is designed for professional use cases where high-quality voice synthesis is essential. It provides users with advanced voice control options, including emotion and pacing adjustments, as well as precise speed and volume settings. The server supports real-time audio streaming and batch processing, making it suitable for both live applications and pre-recorded content. With support for multiple audio formats like WAV, MP3, FLAC, and OGG, it caters to various use cases from web streaming to archival storage. The server is also equipped with robust queue management to handle multiple concurrent requests efficiently. Integration with the Model Context Protocol (MCP) allows for seamless AI model integration, enhancing the server's capabilities with tools for synthesis, batch processing, and voice management.

Features

  • Advanced Voice Control with emotion and pacing adjustments
  • Real-time audio streaming and batch processing
  • Support for multiple audio formats: WAV, MP3, FLAC, OGG
  • Robust queue management for handling concurrent requests
  • Integration with Model Context Protocol (MCP) for enhanced capabilities

Tools

  1. synthesize_speech

    Convert text to natural speech with full control over voice characteristics.

  2. batch_synthesize

    Process multiple text segments efficiently with optional merging.

  3. get_voices

    Retrieve complete voice information and capabilities.

  4. get_status

    Check processing status for synthesis requests.

  5. cancel_request

    Cancel active synthesis operations.

  6. list_output_files

    Browse saved audio files with metadata.