I’m a solo founder with a computer science background. Over the past one month, I’ve been building VO3AI, a browser-based AI video platform powered by Google’s Veo3 model.

You can enter a text prompt or upload an image, and it generates a short video with synchronized voiceover and music — all through a clean UI, no code needed. It’s designed for creators, marketers, or anyone interested in quick visual storytelling with AI.

We’ve been live for about a month. The Veo3 model supports up to 8s video clips; we’ve also integrated other models for 5–10s outputs. Currently profitable with real users, but still iterating on prompt controls, quality, and performance.

Would love to hear your feedback — especially from those working in generative video or building around large models. Open to partnerships or use cases around bulk/API as well.

Well done! Did you happen to vibe code this?