DENVER—Wowza has announced the general availability of Wowza Video Intelligence Framework, a new solution that enables media and sports organizations to apply AI directly inside live streaming workflows, generating real-time metadata, clips, alerts, and machine-readable event signals while a stream is still live.
Built to run alongside Wowza Streaming Engine, the framework connects live video to AI inference and converts what happens inside a stream into outputs downstream systems can immediately use. A single moment in a stream can simultaneously generate metadata for ad targeting, trigger a clip, fire a webhook, and update a downstream system without a separate pipeline, manual handoff, or delay, the company reported.
Rapid delivery of clips and highlights could boost revenue, the company said. Research from StreamLayer's 2026 live sports monetization analysis found that event-triggered, contextually aware ads deliver 40% higher CPMs than standard ad breaks but only if broadcasters have real-time signal about what is happening in the content. When Messi scored his first MLS goal, over 4 million people watched the clip in the hour after it happened. A clip that surfaces the next morning is a different asset entirely.
"Live video is the most valuable, most perishable asset in media and sports, and most of it still goes unused," said Krish Kumar, CEO of Wowza. "The moment passes before anyone can act on it. Video Intelligence Framework puts AI inside the live workflow, where the value actually is, so teams can detect what's happening and do something about it while it still matters."
Wowza Video Intelligence Framework extracts frames from live streams, routes them to AI models for inference, and converts the results into structured outputs that downstream systems can immediately consume - including webhooks, JSON, ID3 tags, stream overlays, timestamped clips, and event logs.
Because the framework operates within the live video pipeline itself, the same detected moment can support multiple outcomes simultaneously, generating ad targeting metadata, triggering an editorial clip workflow, surfacing a production alert, and updating a scouting platform in a single pass.
The framework supports deployment on-premises, at the edge, in the cloud, and in hybrid environments, allowing organizations to run inference close to the source rather than routing all workloads through the cloud. Teams can bring their own AI models and tailor detection logic to their specific use cases, evolving their workflows over time without rebuilding the streaming infrastructure underneath.
In launching the solution the company laid out a number of use cases for media and sports:
- Contextual Advertising and Monetization. Generate real-time content signals, including sponsor-relevant context, natural break points, scene-level metadata, and route them into ad decisioning and dynamic insertion workflows while inventory is still live. The result is more targetable, higher-value ad placements without added latency or manual effort.
- Live Content Tagging, Metadata, and Clip Generation. Identify meaningful moments inside live streams and generate timestamped clips that feed automatically into editorial tools, clip libraries, and distribution pipelines. Content teams produce more usable inventory from the same event, without the manual review process that erodes timeliness and scale.
- Sports Highlights, Scouting, and Performance Analysis. In sports, the framework helps organizations surface the exact clip a scout or analyst needs before the next game, generate player- and event-specific highlights for distribution, and convert live feeds into structured data that flows into coaching, analytics, and performance systems.
- Camera Health and Operational Monitoring. Detect degraded image quality, obstructed lenses, and misaligned feeds in real time, routing alerts into monitoring dashboards and operations workflows before a broadcast is disrupted or a subscriber notices.
- Built to Fit Existing Infrastructure. Wowza Video Intelligence Framework is designed to work with existing Wowza Streaming Engine deployments, allowing organizations to begin applying AI to live workflows without a large-scale infrastructure rebuild. As models, use cases, and business needs evolve, organizations can adapt the intelligence layer without reworking the streaming foundation underneath.
Wowza Video Intelligence Framework is generally available beginning April 19, 2026. Wowza will be showcasing the framework at NAB Show 2026 and in dedicated media and customer briefings focused on live video, sports, and streaming innovation.
For more information, visit wowza.com/video-intelligence-framework
