AI & VideoTechnical DevelopmentMay 11, 2026
Google’s Gemini is testing an early video model called Omni
Google is developing a new video generation model named "Omni" for its Gemini AI platform. Early demonstrations suggest the model can produce video at a qualitative level that is described as impressive.
Key Takeaways
- Omni is a new video generation model being developed for Google’s Gemini AI platform.
- Early demonstrations of Omni are described as producing video with “some pretty impressive” initial results.
- The article frames video generation as an active area of development inside Gemini.
- No release date, product rollout, or technical benchmark is included in the report.
Why It Matters
Google is signaling that Gemini’s video efforts are moving beyond a concept stage and into early demos. For streaming teams, that matters because video generation is becoming a core capability inside major AI platforms, not just a side feature. The article does not give product timing or technical specs, so the main signal is that Omni exists and is already showing visible output. What to watch next is whether Google publishes a public demo, model name in-product, or any benchmark details tied to Gemini.
Read full article at 9to5google.com