Hey Product Hunt 👋 We built Gemini Omni to make advanced AI video creation feel less like operating complicated editing software and more like having a conversation with a creative partner. Most AI video workflows still involve jumping between separate tools for prompting, image references, video generation, editing, and upscaling. We wanted to bring those steps together into one browser-based workflow. With Gemini Omni, you can: 🎬 Generate videos from natural-language prompts 🖼️ Use images and video as creative references 💬 Refine scenes through conversational instructions 🎥 Control characters, scenes, camera movement, and visual direction ✨ Iterate from quick drafts to high-resolution outputs The platform is built for creators, filmmakers, marketers, designers, and anyone experimenting with multimodal video generation. New users can start with free credits, with no credit card required. We'd especially love feedback from the Product Hunt community on the multimodal workflow and the overall creation experience. What would you most want to control through conversation when creating an AI video?

Gemini Omni

Create AI videos from text, images, video, and audio

Create AI videos from text, images, video, and audio