MCP Server Hume

🚀 Hume MCP Server

Collaborate with AI assistants to build your Text-to-Speech (TTS) project.

Hume's MCP Server enables you to use Octave Text-to-Speech (TTS) in AI chat applications through an MCP client application such as Claude Desktop, Cursor, or Windsurf.

Octave TTS is the first text-to-speech system based on large language model (LLM) intelligence. Octave is a speech model that understands contextual meaning, enabling a new level of expressiveness and nuance. It interprets the source text rather than simply pronouncing it.

Watch this video to learn how to use the MCP Server to dub scenes in an audiobook.

🚀 Quick Start

Copy the following content into your client's MCP configuration (e.g., in the .mcpServers property of claude_desktop_config.json or in Cursor's mcp.json):

{
    ...
    "hume": {
        "command": "npx",
        "args": [
            "@humeai/mcp-server"
        ],
        "env": {
            "HUME_API_KEY": "<your_hume_api_key>",
        }
    }
}

✨ Prerequisites

• A Hume AI account and an API Key Get it here
• Node.js
• (Optional) A command-line audio player
  • It is recommended to use ffplay from FFMpeg, but the server will attempt to detect and use several common players.

✨ Available Tools

The server exposes the following MCP tools:

• tts: Synthesize (and play) speech from text
• play_previous_audio: Replay the previously generated audio
• list_voices: List available voices
• save_voice: Save the generated voice to your library
• delete_voice: Delete a voice from your library

✨ Command-Line Options

Options:
  --workdir, -w <path>       Set the working directory for audio files (default: system temporary directory)
  --(no-)embedded-audio-mode Enable/disable embedded audio mode (default: false)
  --(no-)instant-mode        Enable/disable instant mode (default: false) (incurs an additional 10% fee)
  --help, -h                 Display this help message

📚 Documentation

This project includes a comprehensive evaluation framework for measuring how AI agents build text-to-speech projects.

🔧 Technical Details

The following are important environment variables:

• HUME_API_KEY: Your Hume API Key