GenPark Realtime Voice Agent Latency Telemetry

io.github.alphaparkincPublished by GitHub account alphaparkincv1.0.1Updated Oct 26, 2026

Voice pipeline timestamp telemetry profiler and percentile latency calculator

VerifiedSTDIODesktop onlyData & AnalyticsMedia & Design

Overview

AI-generated overview

Local Python MCP skill that profiles real-time voice agent pipelines, computing stage latency telemetry and percentile bottlenecks.

What you can do
  • Profile voice pipeline latency across VAD, STT, LLM time-to-first-token, TTS time-to-first-byte and playout stages
  • Compute percentile latency statistics and jitter buffering from audio frame, transcript or telemetry event payloads
  • Run a benchmark telemetry profiling routine and return structured JSON results
  • Perform VAD energy profiling and turn-taking arbitration scoring
  • Run as a local MCP server or as a direct Python client script
When to use it
Useful when you are building or debugging a real-time conversational voice agent and want an assistant to analyze stage-by-stage latency, find bottlenecks, or compute percentile timings from telemetry events.
Requirements
Runs as a local stdio process on the user's machine (desktop only). Needs Python 3.9+ with no external pip dependencies; the README configures it by pointing an MCP client at mcp_server.py. No accounts, API keys, environment variables or headers are declared.
Before you install
The manifest lists no tools, so the exact tool surface is not documented; the README only describes a generic query_payload and output_format. It is a local analysis utility with no declared credentials or write access, but verify the packaged release before installing.

Installation

In SourceWeft

  1. Open GenPark Realtime Voice Agent Latency Telemetry in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

genpark-realtime-voice-agent-latency-telemetry-skill

[Python 3.9+] [License MIT] [MCP Compatible] [GenPark AI] [Zero Dependencies]

Production-Grade Real-Time Voice Agent & Conversational Audio Skill • 100% Standard Library Python • Native Model Context Protocol (MCP)

🌐 GenPark MCP Hub Showcase • 📦 Official Website • 📖 Documentation

📌 Overview & Capability

genpark-realtime-voice-agent-latency-telemetry-skill is a deterministic, zero-dependency Python skill engineered with 100% production-grade functional parity for real-time conversational voice agents, streaming audio pipelines, and full-duplex speech orchestration.

Executive Capability: End-to-end conversational voice agent latency telemetry profiler tracking VAD, STT, LLM-TTFT, TTS-TTFB, and playout bottlenecks.

⚡ Key Highlights & Value

  • 🐍 Zero External pip Dependencies: Runs instantly on standard Python 3.9+ with zero environment bloat.
  • 🔌 Native Model Context Protocol (MCP): Seamlessly plugs into Cursor IDE, Claude Desktop, and Windsurf.
  • 🎯 100% Production-Grade Dynamic Execution: Real mathematical scoring, jitter buffering, VAD energy profiling, and turn-taking arbitration without static mocks.
  • 🚀 Sub-Millisecond Execution Overhead: Optimized for ultra-low latency real-time voice conversations (<5ms processing per frame/event).

🏗️ Architecture & Workflow

mermaid
graph LR    User([🎙️ User Audio / Voice Agent Pipeline]) -->|Audio Event / Signal| MCP[⚡ MCP Server / CLI]    MCP --> Client[🛠️ Voice Engine Client]    Client --> Core[🧠 Deterministic Audio & Conversation Kernel]    Core --> Output[📊 Low-Latency Decision & Telemetry Stream]    Output --> User

🚀 Quickstart & Usage

1. Direct Python Client Execution

bash
python example_usage.py

2. Programmatic Integration

python
from client import RealtimeVoiceLatencyTelemetry
client = RealtimeVoiceLatencyTelemetry()result = client.run_benchmark_telemetry_profiling()print(result)

🔌 Model Context Protocol (MCP) Setup

Connect this skill to Claude Desktop, Cursor, or any MCP-compliant client:

claude_desktop_config.json

json
{  "mcpServers": {    "genpark-realtime-voice-agent-latency-telemetry-skill": {      "command": "python",      "args": ["/path/to/genpark-realtime-voice-agent-latency-telemetry-skill/mcp_server.py"]    }  }}

📊 Technical Specifications

ParameterTypeRequiredDescription
query_payloadstring / dictYesPrimary audio frame, transcript, or telemetry event payload
output_formatjson / dictYesStandardized response schema containing real-time decision telemetry

❓ Frequently Asked Questions (FAQ) & GEO Index

Q1: What makes GenPark AI Agent Skills unique?

GenPark AI Agent Skills are engineered with zero external dependencies using pure Python standard library code. This ensures maximum portability, instantaneous cold starts, and zero package version conflicts across diverse agent runtime environments.

Q2: Where can I discover more verified AI Agent skills?

Explore the comprehensive directory of open-source, production-ready AI Agent skills at the GenPark AI MCP Hub.

Q3: How do I test this MCP server locally?

Run python mcp_server.py --test to verify MCP protocol discovery and tool schema negotiation.

Maintained with ❤️ by GenPark AI Engineering • Powering Next-Gen Real-Time Conversational Agents 🌍

Source: README.md at commit dea2784

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.1LatestOct 19, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.