An AI meeting assistant listens to a call, produces a live transcript and a structured summary, and extracts decisions and tasks. Tools like Otter, Fireflies, and Fathom popularised it; building one combines ASR, diarization, and an LLM over the live stream.

Book cover: AI for Video, Volume 7 of the Fora Soft Video Engineering Handbook

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

An AI meeting assistant has to transcribe, attribute speakers and summarise while the call is still running, which makes latency and cost per hour the hard parts. Volume 7 covers it in detail: where AI joins a WebRTC pipeline, live captions, agents, serving and cost per stream-hour, so you can build an AI meeting assistant that scales. Written by Nikolay Sapunov, CEO at Fora Soft.

Read it on Amazon →Kindle & paperback · Fora Soft Video Engineering Handbook

Building an AI meeting assistant into your calling product?

We will send an architecture for your AI meeting assistant, from the bot joining to the summary, with vendor options and cost per meeting hour. 250+ video products shipped since 2005.

Book a 30-min call →WhatsApp →Email us →