Introduction

OpenReader is an open source text-to-speech document reader built with Next.js. It provides a read-along experience with narration for EPUB, PDF, TXT, MD, and DOCX documents.

Previously named OpenReader-WebUI.

It supports multiple TTS providers including OpenAI, Replicate, DeepInfra, and custom OpenAI-compatible endpoints such as Kokoro-FastAPI, KittenTTS-FastAPI, and Orpheus-FastAPI.

✨ Highlights

• 🧱 Layout-aware PDF Parsing
  • PP-DocLayoutV3 (ONNX) detects structured blocks with cross-page stitching and geometry-based highlighting for precise read-along sync and clean TTS segmentation
• ⏱️ Word-by-word Highlighting via ONNX Whisper alignment
  • Powered by the external compute worker control plane (NATS JetStream-backed)
• ⚡ Segment-based TTS Playback
  • Sentence-aware generation with cached audio segments, background preloading, and resumable playback across EPUB, PDF, TXT, MD, and DOCX
• 🎯 Multi-Provider TTS Support
  • Self-hosted: Kokoro-FastAPI (multi-voice combinations), KittenTTS-FastAPI, Orpheus-FastAPI, or any custom OpenAI-compatible endpoint
  • Cloud: OpenAI (tts-1, tts-1-hd, gpt-4o-mini-tts), Replicate (built-in catalog + any model ID), DeepInfra (Kokoro-82M and others)
• 🎧 Audiobook Export in m4b/mp3 with resumable chapter generation
• 🗂️ Flexible Backend — embedded SeaweedFS or S3-compatible storage, SQLite or Postgres, server library import, and device sync
• 🔐 Auth and User Isolation — auth is required in v4+, with optional anonymous auth sessions for guest flows
• 🎨 Customizable — 13 built-in themes (light and dark palettes), per-user TTS settings, and document handling controls

🧭 Key Docs

• Docker Quick Start
• Local Development
• Vercel Deployment
• Environment Variables
• Auth
• Database
• Object / Blob Storage
• Migrations
• Server Library Import
• TTS Providers

Source Repository

• GitHub: richardr1126/openreader