Launching today

Gemini Omni

Launching today

Free AI video generator powered by Google's omni-modal model

5 followers

Free AI video generator powered by Google's omni-modal model

5 followers

Visit website

Gemini Omni turns text, images, video, and audio into cinematic AI video — all in one prompt. Powered by Google's omni-modal model with native synced audio, in-chat editing, and character consistency. Free users get 720P; subscribers unlock 1080P/4K without watermark. No complicated workflows — just describe what you want and iterate in chat.

Free Options

Launch tags:Social Media•Artificial Intelligence•Video

Launch Team

Mina - Meeting AssistantTalks like a Teammate. Powered by Skills

Promoted

Maker

📌

Hey PH community! 👋 I'm Ethan, the maker of Gemini Omni. I built this because existing AI video tools felt fragmented — you'd need one tool for text-to-video, another for audio, another for editing. Gemini Omni combines everything into one conversational workflow powered by Google's omni-modal model. What makes it different: 🎬 Multimodal input: mix text, image, video, and audio in a single prompt 🔊 Native synced audio — no separate step needed 💬 In-chat editing: iterate on your video in conversation 🆓 Genuinely free to start (720P, no credit card) Would love your feedback and questions! What kind of videos would you most want to create?

Report

2d ago