How abd-ul-hannan/my-assistants works
Project type and purpose
• This is a single-page, full-stack presentation creator (front-end only) built with React 18 + TypeScript, styled with Tailwind CSS, and bundled with Vite.
• It transforms a user’s topic into a short AI-generated script, synthesizes voice via ElevenLabs, produces an AI talking-head video via Tavus, and displays progress in real time.
File structure
• Top level:
• index.html, src/, package.json, Vite/Tailwind/TypeScript configs, .env for API keys.
• src/
• components/: React UI (SplashScreen, MainInterface, ProgressIndicator, GenderSelector, ResultsDisplay).
• services/: orchestration & wrappers for external APIs (scriptGenerator.ts, apiService.ts, elevenLabsService.ts, tavusService.ts).
• config/: presenter metadata (male/female IDs).
• types/: shared TypeScript definitions.
• No custom backend – client directly calls third-party APIs.
README for additional insights
• UX flow: topic in → script (~5s) → voice (~10s) → video (1–3 min)
• Fallback: if video times out, uses demo videos
• Deployment target: Netlify (static hosting)
• Key external dependencies: ElevenLabs Text-to-Speech API, Tavus Video Generation API