genpark-voice-vad — Claude Code MCP server
Decides whether a speaker has finished their turn, using precomputed dB energies plus a transcript. Useful in voice bots and dialogue pipelines.
Open on GitHubWhat genpark-voice-vad does
The server reads dB energy values and a transcript that you already have. It never decodes audio, never transcribes speech, and runs no trained VAD model. Confidence numbers are heuristic scores rather than calibrated probabilities, so feeding them into thresholds tuned for a real model will mislead you.
Four tools ship with it: analyze_turn_status, calibrate_acoustic_thresholds, predict_semantic_closure and run_benchmark_turn_detection. Calling tools/list returns the required arguments and their JSON schemas. State lives per MCP process, and benchmark tools use isolated instances.
Python 3.9 or newer is required. Neither the library nor the stdio server pulls in runtime dependencies. Install comes from the wheel attached to the GitHub release, since PyPI publication is still pending — pip install genpark-voice-vad is not available. When the genpark-voice-vad command is missing from PATH, point to its absolute path or run python -m genpark_voice_vad with the same interpreter you installed into.
What it helps with
- tell from a transcript whether someone finished speaking or is just pausing
- tune energy thresholds against a specific recording
- score semantic closure before the bot replies
- benchmark turn detection on your own data
- add endpoint detection to an MCP client without audio libraries
Example prompts for the agent
- Check this transcript and energy series to see if the speaker finished their turn
- Calibrate the acoustic thresholds for this recording
- Run the turn detection benchmark on my test set
How to install genpark-voice-vad
Install
The MCP registry has no launch command for it: see the repository README
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about genpark-voice-vad
How do I install genpark-voice-vad in Claude Code?
Install the wheel from the GitHub release first: `python -m pip install https://github.com/Alpha-Park/genpark-voice-turn-taking-endpoint-detector-skill/releases/download/v1.0.1/genpark_voice_vad-1.0.1-py3-none-any.whl. Then register the server in your MCP client config with the command genpark-voice-vad` and an empty args list.
What does genpark-voice-vad do?
It detects the endpoint of a spoken turn from precomputed dB energies and a transcript. Four MCP tools return heuristic confidence scores.
Does it need extra dependencies?
Python 3.9 or newer is enough for the library and the stdio server, with no runtime dependencies. The .mcpb bundle from the release also expects a Python 3.9+ interpreter on PATH.
