live-audio-intelligence-mcp

MCP server for live financial webcast transcription and heuristic vocal stress analysis.

Turns any live webcast URL (earnings calls, CNBC, investor days) into a real-time pipeline that feeds an LLM two things simultaneously:

1. A rolling transcript via faster-whisper (CPU, int8).
2. A heuristic vocal stress score (0–100) derived from F0 pitch jitter, hesitation ratio, and voiced-frame fraction. These prosodic features are well-established correlates of speaker arousal in the vocal-analysis literature; their composition into the score below is heuristic and has not been empirically validated against market outcomes. Treat it as a coarse signal, not an oracle.

Built on the Model Context Protocol. Exposes 4 tools over stdio; drop it into Claude Desktop, Claude Code, or any MCP client.

Why this exists

Sell-side analysts and hedge-fund PMs don't just want to read the earnings transcript after the fact — they want a real-time signal about how confident the CFO sounds when asked about Q4 guidance. This server wires a Whisper pipeline and a pYIN-based prosody analyzer directly into an LLM's tool loop, so the model can ask "what did the CEO just say about China?" and "how stressed did they sound saying it?" in the same conversation.

Install

1. System prerequisite — FFmpeg

FFmpeg is a system binary, not a Python package. The ffmpeg-python wrapper is not a dependency here — we drive the binary directly via subprocess. You must install it yourself.

macOS (Homebrew):

brew install ffmpeg

Linux (Debian / Ubuntu):

sudo apt-get update && sudo apt-get install -y ffmpeg

Linux (Fedora / RHEL):

sudo dnf install -y ffmpeg

Windows — choose one:

# Option A — winget (Windows 10/11)
winget install --id=Gyan.FFmpeg -e

# Option B — Chocolatey
choco install ffmpeg

# Option C — Scoop
scoop install ffmpeg

Confirm it's on your PATH:

ffmpeg -version

If the command errors with "not found", reopen the terminal (PATH changes don't propagate to already-open shells) or add the ffmpeg bin/ directory to your PATH manually.

2. Python package

Requires Python ≥ 3.10.

pip install live-audio-intelligence-mcp

Or run directly without installing with uv:

uvx live-audio-intelligence-mcp

The first run will download the faster-whisper base.en model (~140 MB) from Hugging Face and cache it under ~/.cache/huggingface/.

Run it

Stdio MCP server:

live-audio-intelligence-mcp

Or equivalently:

python -m live_audio_intelligence_mcp

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "live-audio-intelligence": {
      "command": "live-audio-intelligence-mcp"
    }
  }
}

Claude Code

claude mcp add live-audio-intelligence -- live-audio-intelligence-mcp

Tools

The stress score

Composite of:

• Pitch jitter (coefficient of vari

... View full README on GitHub