Google Gemini Omni Flash Launches Conversational Video Creation and Editing Tools
Google has introduced Gemini Omni Flash, a multimodal model for creating and refining video through conversation across Gemini, Flow, and YouTube Shorts.
Google has introduced Gemini Omni Flash, the inaugural model in its Omni family, for multimodal video generation and editing. The model is designed to let users create and refine video through conversation, using inputs that can include text, images, video, and audio. It is rolling out through the Gemini app and Google Flow for Google AI Plus, Pro, and Ultra subscribers, with YouTube Shorts support and API access planned for developers.
The important distinction is that Google’s public materials describe the launch as Gemini Omni Flash, not a numbered "Gemini Omni 1.1 Flash" release. Google has also not publicly documented claims of 4K upscaling, first and last frame controls, or a 360p drafting mode. For teams evaluating the technology, the available product information points instead to conversational creation, multi-turn editing, and the ability to keep a scene coherent while making changes.
What Gemini Omni Flash adds to Google's video tools
According to Google's official Gemini Omni announcement, Omni Flash can generate and edit video through a conversational workflow. Rather than requiring a user to produce a final prompt in one attempt, the model supports multi-turn refinement. That approach matters because video work often involves incremental requests, such as changing an element, revising a sequence, or iterating on a creative direction.
Google also positions Omni Flash as a model grounded in Gemini's knowledge. The company emphasizes that it can reference multiple input types and maintain scene coherence across edits. In practical terms, this makes the model relevant to video workflows where the starting point is not only a text prompt, but also existing creative material.
The documented capabilities include:
- Video generation and editing through conversation
- Multi-turn refinement of generated or edited content
- Multimodal references from images, text, video, and audio
- An emphasis on maintaining scene coherence across edits
- A built-in SynthID watermark intended to support verifiability
SynthID is particularly notable in a video creation product because it gives Google a mechanism to identify AI-generated content. The announcement frames the watermark as part of its approach to making generated video verifiable.
Availability across Gemini, Flow, and YouTube Shorts
Google says Gemini Omni Flash is launching to Google AI Plus, Pro, and Ultra subscribers through the Gemini app and Google Flow. It also has YouTube Shorts support. This places the model across consumer-facing creation surfaces as well as Flow, Google's filmmaking-oriented tool.
Developers should note that API availability is described as upcoming. Google has not, in the supplied materials, provided public API specifications, pricing, or a launch timetable for that access. Businesses planning automated video workflows should therefore treat direct integration as a future possibility rather than a currently documented capability.
What is documented and what is not
The public launch information supports a clear picture of the model's core purpose, but it does not support every feature claim associated with the purported "1.1" version. The distinction is important for buyers and creators comparing tools or planning production processes.
| Area | Gemini Omni Flash in Google's public materials | Not stated in the official launch materials |
|---|---|---|
| Model name | Gemini Omni Flash | A Gemini Omni Flash 1.1 version |
| Creation workflow | Conversational video generation, editing, and multi-turn refinement | A named 360p drafting mode |
| Creative controls | Multimodal inputs and scene coherence across edits | 4K upscaling and first or last frame controls |
| Developer access | API access is planned | Public API pricing, specifications, or timing |
How it fits into the Gemini ecosystem
Omni Flash extends Google's Gemini ecosystem into video creation and editing, while Veo remains a related cinematic generation capability referenced in the model documentation. Google also references related Omni and Flash variants, including Gemini 3.5 Flash-Lite, but the supplied materials do not establish a feature-by-feature comparison between those models and Omni Flash.
For a business, the immediate opportunity is less about replacing a full video production stack and more about shortening early creative cycles. A marketing team could use conversational iteration to explore a concept, revise visual material, or turn existing assets into new video directions. However, the lack of documented API details means companies should avoid designing production automation around integration assumptions that Google has not yet published.
If Gemini and other AI assistants are becoming part of how customers discover products, services, and expertise, visibility in those answers deserves the same attention as traditional search. Scalevise can help you measure where your brand appears, identify gaps in AI-generated results, and prioritize practical improvements with the AI Visibility and GEO Checker. Start an AI Visibility scan.
Frequently Asked Questions
What is Gemini Omni Flash?
Gemini Omni Flash is Google's inaugural Omni-family model for multimodal video generation and editing through conversation.
Where is Gemini Omni Flash available?
Google says it is launching to Google AI Plus, Pro, and Ultra subscribers through the Gemini app and Google Flow, with YouTube Shorts support.
Does Google offer a Gemini Omni Flash 1.1 model?
Google's public materials cited here refer to Gemini Omni Flash and do not reference a model named Gemini Omni Flash 1.1.
Does Gemini Omni Flash have an API?
Google says API access is upcoming. The supplied public materials do not provide API specifications, pricing, or a release timetable.
Does Gemini Omni Flash support 4K upscaling or first and last frame controls?
Those capabilities are not explicitly documented in the primary Google materials for Gemini Omni Flash.
Conclusion
Gemini Omni Flash is a confirmed Google video creation and editing model built around multimodal inputs and conversational refinement. Its current rollout gives eligible Gemini subscribers and Flow users access to the model, while planned API access may broaden its business applications later. The publicly documented story is the launch of Omni Flash itself, not a numbered 1.1 update or the unconfirmed feature set associated with that label.