Nvidia · NVIDIA Blog
At the IBC conference, running Sept. 11-14 in Amsterdam, the creative
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
★ Tier-1 Source
Read on to learn more about what NVIDIA’s highlighting at the show.
Key facts
- Wowza, whose Wowza Streaming Engine media server technology powers more than 35,000 video deployments across over 170 countries, will distribute SVD through the Wowza Video Intelligence Framework
- Since its initial release, SVD’s accuracy has reached 99.3% for text-to-video content and 97.7% for image-to-video content, with especially large gains on difficult image-to-video cases
- Studio Voice includes new Microphone Profiles built on NVIDIA Studio Voice NIM microservices, giving users more control over the tonal character of enhanced speech
- Wowza is integrating vision language models, including NVIDIA Cosmos 3 and Nemotron, into the Wowza Video Intelligence Framework, fine-tuned through…
Summary
At the IBC conference, running Sept. 11-14 in Amsterdam, the creative, technology and business communities are coming together to turn ideas into action and discuss innovations across the media and entertainment industries. Media companies are increasingly integrating AI into live production, sports, news and streaming workflows to unlock richer performance insights, verify video authenticity, and enhance and localize content, all without disrupting trusted broadcast environments. At IBC 2026 in Amsterdam, NVIDIA announced a major expansion to NVIDIA AI for Media, a collection of GPU-accelerated software development kits (SDKs), NVIDIA NIM microservices, playbooks, and blueprints that enhance audio, video and augmented-reality effects for media and entertainment workflows, to unlock new ways to understand motion, verify and enhance video, localize programming and build AI-powered media applications.
Since its initial release, SVD’s accuracy has reached 99.3% for text-to-video content and 97.7% for image-to-video content, with especially large gains on difficult image-to-video cases.