Rich Text Voiceover Video Generator

I want a straightforward tool that lets me write or paste rich-formatted text—bold, italics, headings, lists—then turn that script into an automatic video. As soon as the text is ready, I should be able to pick a male or female text-to-speech voice and have the system generate the narration and sync it with the on-screen text, finally exporting a share-ready MP4. Core workflow I’m after 1. Compose or edit content in a WYSIWYG field that preserves formatting. 2. Click “Generate” to create a voiceover using text-to-speech (male and female voices available). 3. The app lays the formatted text onto slides or animated captions, times them to the audio, and renders a video preview. 4. Download or publish the final video without extra manual steps. Acceptance criteria • Web or cross-platform desktop app, clean UI, no installation hurdles • Rich text editing must support at least headings (H1-H3), bold, italics, bullet/numbered lists, and hyperlinks • Built-in TTS with both male and female voices in clear, natural quality • Automatic slide/caption timing that matches the generated audio end-to-end • Export to MP4 (1080p minimum) within reasonable render time • Source code and brief setup/run instructions provided on delivery Tech stack is flexible—I’m familiar with React, Node, FFmpeg, AWS Polly, and Google Cloud TTS, but I’m open to alternatives that achieve the same smooth, single-click experience.

Project ID: 40561210