Gemini Omni (Omni Flash)
Gemini Omni Flash makes video from mixed image, audio, video and text input and edits it conversationally; first of a planned family.
Fuses Gemini's reasoning with generation, so edits across turns keep characters and physics consistent. Rolled out in the Gemini app, Flow and YouTube Shorts; API preview 2026-06-30, GA as Omni 1.1 Flash 2026-08-27.
- Date
- Tuesday, 19 May 2026
- Lab
- Google DeepMind
- Kind
- model
- Access
- closed API
Successor direction to Veo; Veo 2 and 3 API models were shut down 2026-06-30 per the changelog.
Sources
- deepmind.google/blog/introducing-gemini-omni/
- ai.google.dev/gemini-api/docs/changelog
- blog.google/innovation-and-ai/technology/ai/google-ai-updates-may-2026/
This record was checked against its sources on 6 October 2026. How we check