One-page planner: the agent-dispatch flow (how an AI participant joins a call), the three Agents voice-pipeline types (STT-LLM-TTS vs realtime vs half-cascade), the 2026 LiveKit Cloud tiers (Build / Ship / Scale / Enterprise) with the WebRTC-minute, agent-minute, and bandwidth meters, the per-minute cost-stack formula, and the build-vs-buy checklist (Cloud vs self-host vs meeting-bot SaaS).
Download free PDF
The book · Volume 7 of 7
AI for Video: A Complete Guide to Intelligence in Video Products: From Real-Time Pipelines and Agents to Serving, Cost, Compliance, and Verticals
This LiveKit meeting assistant cheat sheet shows how an AI participant joins a call, compares the three voice-pipeline types and works out per-minute cost across LiveKit Cloud tiers. Volume 7 covers this in detail: agents as engineering, real-time latency budgets in WebRTC, serving infrastructure and cost per stream-hour. Written by Nikolay Sapunov, CEO at Fora Soft.
Building an AI meeting assistant on LiveKit and need the per-minute cost before you commit?
Tell us your meeting volume and features, and we will pick the voice pipeline, compare LiveKit Cloud with self-hosting and give you a per-minute cost. 250+ video products shipped since 2005.
You get a realistic estimate, technical recommendations and next steps. Free, no obligations.
