Built an AI Video Generator Application with 9+ Models – My Journey with TOVIDEO

Hey Indie Hackers,

I just launched TOVIDEO, an AI-powered app that generates cinematic videos from text prompts or still images — no editing skills required.

Why I built it this application?

I’ve been experimenting with AI video tools for months and found most were either locked to one model, expensive, or lacking flexibility. I wanted something that gave creators multiple AI options, easy controls, and professional-quality output without the complexity.

Tech stack for the app:

Frontend: React Native (iOS)

Backend: Firebase + custom APIs to connect with multiple AI video models (Google Veo 3, LTX Video, Pixverse v4.5, etc.)

Payments: RevenueCat (subscriptions + credit packs)

Features:

9+ AI models in one place

Text-to-video & image-to-video in 1080p HD

Multiple aspect ratios & durations

Credit-based system for flexible usage

🚀 What’s next

Longer video generation

More creative templates & effects

I’d love feedback from the community on:

Which additional features would make you try it?

Thoughts on credit-based vs. subscription-only pricing

UI/UX improvements you think are important for an AI tool

Check it out here: https://apps.apple.com/US/app/ai-video-generator-tovideo/id6748954744