home / mcp / mcp audio server

MCP Audio Server

Provides text-to-speech and audio playback for MCP clients with real-time status and audio control.

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "batchlion-mcp-audio-server": {
      "command": "/path/to/your/python",
      "args": [
        "/path/to/mcp-audio-server/audio_server.py"
      ]
    }
  }
}

You can run an MCP Audio Server that provides text-to-speech and audio playback for Claude Desktop and other MCP clients. This server handles high-quality TTS (with smart language handling), plays common audio formats, and lets you control and monitor audio in real time. The setup emphasizes practical steps so you can install, configure, and start using audio features quickly.

How to use

Once your MCP Audio Server is running, you can perform common actions through your MCP client: convert text to speech with optional rate, volume, and voice controls; play audio files; stop playback; and check the current audio status. For Chinese text, the system automatically uses Google TTS for natural-sounding speech. For other languages, you can list and choose from system-installed voices. You can also adjust playback rate and volume to tailor the listening experience.

How to install

Prerequisites: Install Python 3.8 or newer, ensure you have Claude Desktop for MCP integration, and confirm your system can play audio.

# 1. Clone the repository
git clone https://github.com/yourusername/mcp-audio-server.git
cd mcp-audio-server

# 2. Install dependencies
pip install -r requirements.txt

# 3. Configure Claude Desktop
# Add the following to your claude_desktop_config.json
```

```json
{
  "mcpServers": {
    "audio-server": {
      "command": "/path/to/your/python",
      "args": ["/path/to/mcp-audio-server/audio_server.py"]
    }
  }
}
```

```markdown
# 4. Restart Claude Desktop to apply changes and start using audio features

Claude Desktop configuration

To integrate with Claude Desktop, add an MCP server entry that points to the Python runtime and the audio_server script.

{
  "mcpServers": {
    "audio-server": {
      "command": "/path/to/your/python",
      "args": ["/path/to/mcp-audio-server/audio_server.py"]
    }
  }
}

Available tools

speak_text

Convert text to speech. Automatically uses Google TTS for Chinese. Accepts text, rate, volume, and optional voice_id for non-Chinese voices.

list_voices

List available TTS voices for non-Chinese languages.

play_audio_file

Play an audio file given a file path with an optional volume control.

stop_audio

Stop the current audio playback immediately.

get_audio_status

Return real-time information about the audio system and current playback.