Frogly - Caption Generation SAAS

Frogly lets users upload videos and automatically generate captions using speech recognition. Users can edit text, adjust timing, and style captions. The final video can embed captions directly or export caption files for platforms, ensuring accessibility, clarity, and engagement across different audiences.

Highlights

Through Frogly, users can upload videos, generate captions automatically using AI, and refine them through editing tools. Captions can be styled with fonts, colors, and backgrounds, then embedded directly onto videos. Ready-made templates optimize content for Instagram, TikTok, and other platforms, making videos more engaging, accessible, and tailored for social media consumption.

Technology

The software is built with a modern web stack using Next.js and React for a responsive, dynamic front-end, with TypeScript ensuring type safety and maintainability. Supabase handles authentication, database storage, and real-time collaboration. Caption generation relies on the Google Speech Recognition AI service for accurate transcription. Once captions are created and styled, FFMPEG is used server-side to embed them directly onto the video, enabling export-ready formats optimised for social media platforms. This combination delivers a scalable, efficient, and user-friendly captioning solution.