Jarvis

Brings AI voice interaction to your browser with optional local Whisper streaming for low-latency transcripts.

typescript

34

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "shantur-jarvis-mcp": {
      "command": "jarvis-mcp",
      "args": [],
      "env": {
        "MCP_VOICE_STT_MODE": "whisper",
        "MCP_VOICE_AUTO_OPEN": "false",
        "MCP_VOICE_HTTPS_PORT": "5114",
        "MCP_VOICE_WHISPER_URL": "http://localhost:12017/v1/audio/transcriptions",
        "MCP_VOICE_WHISPER_TOKEN": "YOUR_TOKEN"
      }
    }
  }
}

Available tools

converse

Start or resume a voice turn with the MCP server; the system handles audio capture, streaming, and AI response orchestration.

voice_status

Query and report the current voice streaming status, indicating whether Whisper or browser STT is active.