Vocaless

Overview

Vocaless is a Model Context Protocol server that removes vocals from local audio files and transposes instrumentals. Any MCP-compatible AI assistant can use Vocaless tools directly within conversations and agent runs, deciding when to apply vocal removal and transposition to your audio.

The server runs locally via the npm package @vocaless/mcp, which communicates over stdio. Installation uses npx -y @vocaless/mcp and requires the VOCALESS_API_KEY environment variable for authentication. Version v0.1.3 is the current release.

Vocaless appears in the File System category on mcp.site and integrates with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and others. If you maintain Vocaless, claim this listing to verify ownership and keep information current. Learn more at https://vocaless.app/docs/mcp.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "vocaless": {
      "command": "npx",
      "args": [
        "-y",
        "@vocaless/mcp"
      ],
      "env": {
        "VOCALESS_API_KEY": "<vocaless-api-key>"
      }
    }
  }
}

Requires VOCALESS_API_KEY