An MCP server that monitors a live webcast URL, transcribes the audio in real time, and computes a vocal stress score from prosodic features. It exposes tools to start monitoring, fetch the rolling transcript, analyze stress over a time window, and stop monitoring.
From the registry: Live webcast transcription + vocal stress analysis (F0 jitter, hesitation) for earnings calls.
$ ffmpeg -version$ pip install live-audio-intelligence-mcpPlease install the `live-audio-intelligence-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Python 3.10+** — Python version 3.10 or newer is required to install and run the MCP server.
- **Install ffmpeg** — ffmpeg must be installed and available on your PATH. You can verify installation with `ffmpeg -version`. Run: `ffmpeg -version`
- **Install the Python package** — Install the MCP server from PyPI using pip. Run: `pip install live-audio-intelligence-mcp`
Optional prerequisites:
- Initial model download — On first run, the server downloads the `faster-whisper base.en` model (~140 MB).
Canonical MCP server config (stdio transport):
- command: `live-audio-intelligence-mcp`
- args: []
Note: The README also lists `python -m live_audio_intelligence_mcp` as an equivalent stdio launch command. No environment variables are documented.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.