Skip to content
mcp/harbor
VS Code

Parlova for VS Code

io.github.fort652/parlova-mcp

Transcribe local audio/video and YouTube into timestamped, speaker-labelled text. 90+ languages.

client:VS Code transport:stdio runtime:pypi

Install Parlova in VS Code

.vscode/mcp.json 

{
  "inputs": [
    {
      "type": "promptString",
      "id": "parlova-token",
      "description": "PARLOVA_TOKEN",
      "password": true
    }
  ],
  "servers": {
    "parlova-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "parlova"
      ],
      "env": {
        "PARLOVA_TOKEN": "${input:parlova-token}"
      }
    }
  }
}

VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs

Parlova in other clients

Parlova MCP server