Solutions / Publishers & broadcasters
Sell the moment, not just the slot.
Edge adds what's on screen going into each break, IAB categories, scene keywords and brands seen on screen, to the ad request you already send, working alongside your playout and ad server.
We read your live stream itself.
Nothing runs on viewers' screens, and no recognition (ACR) on the TV is needed. If Edge can see your stream, it can read it, on any screen your stream reaches.
Reads the live channel
Edge follows your stream: the picture, what is said, and the text and logos on screen.
Holds context through the break
When the break starts, what was on screen just before it is kept. Adverts never overwrite it.
Adds it to your request
Your ad system asks for the context before its ad request and adds two short lists: categories and keywords.
Built to sit beside you
Nothing in your chain changes.
Edge does not replace your playout, your ad server or your buyers, and it does not choose ads or set prices. It answers one question at each break: what was on screen going into it?
If the answer is not ready, it is empty and your request goes out as it always would. Edge can add information; it cannot block a request.
You can also guide it in plain words: topics to favour or avoid, brands you work with.
Market context
Buyers already pay attention to content.
As third-party market data: CTV ads with a genre signal earned 27% higher CPMs, per Beachfront.
(reported by Digiday; not an Edge result). Edge reads the scene, which is finer than the genre.
The proof
How we measure it.
What Edge reads on live streams, and how each measurement was taken, is published by Edge Research.
11.18M
products and deals matched to live TV scenes
5.14M
content tags published
434
different ad categories read from live feeds
Edge production records, October 2024 to 14 November 2026. Edge team traffic is left out.
Guides
IAB categories in live ad requests
How those categories are added to the request you already send.
Schedule data vs on-screen context
What the planned slot describes, and what the live picture describes.
Speech and on-screen text
How what's said, and the text and logos on screen, enrich the request.
AWS Elemental Inference alternative
Live context when you are not on AWS Elemental.