danvics/openreader
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
openreader/docs-site/docs/introduction.md
Richard R 874e5ef359 refactor(whisper): migrate word alignment to ONNX backend and remove whisper.cpp integration 
Replace the previous whisper.cpp-based word alignment with a fully ONNX-based
implementation using onnxruntime-node and @huggingface/tokenizers. Add new
Whisper ONNX model management, alignment mapping, and spectral analysis modules.
Remove all code and documentation referencing whisper.cpp, update environment
variables, Dockerfile, and docs to reflect ONNX-only alignment. Add unit tests
for alignment and ONNX model logic.
2026-05-19 13:00:21 -06:00

2.9 KiB
Raw Blame History

id title slug
intro 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

  • 🎯 Multi-Provider TTS Support
    • Kokoro-FastAPI: supports multi-voice combinations (for example af_heart+af_bella)
    • KittenTTS-FastAPI: lightweight, CPU-friendly self-hosted TTS
    • Orpheus-FastAPI
    • Custom OpenAI-compatible: any TTS API with /v1/audio/voices and /v1/audio/speech endpoints
    • Cloud TTS providers:
      • Replicate: includes a built-in catalog and supports any Replicate model ID via Other
      • DeepInfra: Kokoro-82M and other hosted models
      • OpenAI API: tts-1, tts-1-hd, and gpt-4o-mini-tts
  • 📖 Read Along Experience
    • Real-time highlighting for PDF/EPUB, with built-in ONNX Whisper word-level timestamps in local compute mode
  • 🛜 Document Storage
    • Documents are persisted in server blob/object storage for consistent access
  • ⚡ Segment-based TTS Playback for reusable generation + preloading
    • Stores segment audio in object storage for fast replay/resume
  • 🎧 Audiobook Export in m4b/mp3 with resumable chapter generation
  • 🔐 Auth Optional by Design
    • Run no-auth for local use, or enable auth with user isolation and claim flow
  • 🗂️ Flexible Storage and Database Modes with embedded defaults or external S3/Postgres
  • 🚀 Production-ready Server Behavior with TTS caching/retries/rate limits and startup migrations
  • 🎨 Customizable Experience
    • 13 built-in themes (light and dark palettes), TTS, and document handling controls

🧭 Key Docs

Source Repository