Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add roedyrustam/vibes-plug --skill voice-ai-realtime-agentgit clone --depth 1 https://github.com/roedyrustam/vibes-plugWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/roedyrustam/vibes-plug/voice-ai-realtime-agent)<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/voice-ai-realtime-agent"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/voice-ai-realtime-agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/voice-ai-realtime-agent"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/voice-ai-realtime-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.03074 |
| Opus 5.5 | $0.00027 | $0.01230 |
| Sonnet 5.5 | $0.00014 | $0.00615 |
| Haiku 4.5 | $0.00007 | $0.00307 |
Grade A, and why
voice-ai-realtime-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice AI Realtime Agent (2026 Edition)
English
Orchestration & Integration
- Speech Models & Multimodal Streams:
ai-llm-integration-expert,gemini-agent-booster,frontier-ai-models-expert - Realtime Protocols & WebSockets:
realtime-collaboration-expert,sse-websocket-streaming-expert - Client Platforms & Audio Processing:
senior-frontend,mobile-expo-expert,apple-ecosystem-expert - Agent Swarms & Tools:
multi-agent-orchestration,parallel-tool-orchestrator,chatbot-messaging-expert - Lifecycle & Governance:
zero-to-prod-orchestrator,session-memory-manager,anti-slop
Description
Expert guide for building ultra-low-latency (<300ms), bi-directional conversational voice AI applications. Covers WebRTC, full-duplex WebSocket audio streaming (PCM 24kHz), OpenAI Realtime API, Gemini Multimodal Live API, LiveKit Agents SDK, and smart interruption (barge-in) handling.
Trigger Conditions
- Applications requiring sub-second, spoken conversation with an AI agent.
- Voice customer service bots, verbal copilots, language tutors, and interactive voice assistants.
- Implementation of WebRTC audio streaming, full-duplex WebSocket audio (PCM 24kHz), and Silero VAD.
- Setting up OpenAI Realtime API (
gpt-5-realtime-preview/gpt-4o-realtime-preview) or Gemini Multimodal Live API.
1. Core Architecture: Full-Duplex Speech-to-Speech
Traditional voice pipelines chain STT ➔ LLM ➔ TTS with cumulative latency exceeding 1,200ms–2,500ms. Modern 2026 voice agents use native speech-to-speech or streamable full-duplex WebRTC pipelines achieving natural, human-like reaction times (~250–350ms).
User Mic ──► [WebRTC / WebSocket] ──► [VAD: Silero / WebRTC VAD]
│
▼
User Speaks <── [Audio Output] ◄── [Native Audio Stream / Cartesia] ◄── [OpenAI Realtime / Gemini Live]
│
└── User Interrupts (Barge-in) ──► Instant Buffer Flush & Cancel Audio Frame Emission
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago Changed · -1 lines 6aa86dd2505f
- 6d ago Changed · +1 lines 6637873693ea
- 7d ago Changed 9d2c4fe20e8e
- 9d ago Changed · +91 lines 0f70bc654650
- 18d ago Changed 192ab894c6d4
- 23d ago Changed 8dd0bf79233e
- 24d ago Changed d6f7aff26ece
- 26d ago Changed · -6 lines · +55 tokens per session f59724763582
- 28d ago Changed · +6 lines · -55 tokens per session d436f111a415
- 1mo ago First seen · 243 lines · 68 tokens per session scan A 3816719b3d9d
voice-ai-realtime-agent is a skill published in the GitHub repository roedyrustam/vibes-plug (114 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 3,074 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-12.
Other skills, from other repositories
ai-engineering-toolkit
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
ai-prompt-regression-testing
Use when comparing prompt changes against a fixed evaluation set: record actual model settings, required checks, missing results, judge limitations and case-level regression evidence.
LLM
Implement large language model (LLM) chat completions using the z-ai-web-dev-sdk. Use this skill when the user needs to build conversational AI applications, chatbots, AI assistants, or any text generation features. Supports multi-turn conversations, system prompts, and context management.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
ai-prompt-regression-testing
Prompt engineering regression test matrix register: baseline outputs, semantic drift thresholds, judge evaluations, and golden dataset.
data-flow-diagram
Design data movement and transformation pipelines. Show how data flows between systems, transforms, and where it's stored. Use when architecting data integrations or ETL processes.