Launching today
ModernReader
Read with rhythm. Feel the words.
2 followers
Read with rhythm. Feel the words.
2 followers
Reading long text is exhausting — your eyes fatigue, your mind wanders, and plain TTS sounds like a robot reading a manual. ModernReader is a multi-sensory AI reading system on the CRA model: parse Markdown/EPUB/TXT, read aloud with rhythm-aware voice, tag emotions (EN & ZH), and AI-summarize. Runs as PWA, desktop, or Capacitor shell — self-host via Docker. Built for deep readers, students, and anyone with visual fatigue. Finalist — 2026 Cross-Strait Entrepreneurship Competition.
Launch Team
Render: Get up to $100K in startup creditsThe fastest way to deploy and scale apps and agents
Promoted
First time here? 👋 I'm TeWei, the maker of ModernReader.
ModernReader started from a simple frustration: long-form reading online is exhausting — your eyes fatigue, your mind wanders, and default TTS sounds like a robot reading a manual. So I built a reading system around the CRA model (Comprehension-Rhythm-Affect): it parses Markdown/EPUB/TXT, reads them aloud with rhythm-aware voice (ElevenLabs or local gTTS/ffmpeg), tags the emotional tone of every passage (joy, sadness, anger, fear, surprise, disgust — in EN & ZH), and summarizes with AI when you're short on time.
It runs anywhere: as a PWA in your browser, a desktop demo, a Capacitor mobile shell — or fully self-hosted with Docker in one command.
If you're a deep reader, a student, or someone whose eyes need a break, I'd love your feedback:
- What's the first thing you'd want to import?
- Which emotion tags feel most useful to you?
- Would you use voice-guided reading on your commute?
Happy to answer any question about the architecture (TypeScript core, CoreML LSTM, FastAPI) — ask away in the comments. ⭐ a star on GitHub helps a lot too!