📄🔊 OpenReader WebUI

OpenReader WebUI is an open source text to speech document reader web app built using Next.js, offering a TTS read along experience with narration for EPUB, PDF, TXT, MD, and DOCX documents. It supports multiple TTS providers including OpenAI, Deepinfra, and custom OpenAI-compatible endpoints like Kokoro-FastAPI and Orpheus-FastAPI

• 🎯 (New) Multi-Provider TTS Support
  • Kokoro-FastAPI: Supporting multi-voice combinations (like af_heart+af_bella)
  • Orpheus-FastAPI
  • Custom OpenAI-compatible: Any TTS API with /v1/audio/voices and /v1/audio/speech endpoints
  • Cloud TTS Providers (requiring API keys)
    • Deepinfra: Kokoro-82M + models with support for cloned voices and more
    • OpenAI API ($$): tts-1, tts-1-hd, and gpt-4o-mini-tts w/ instructions
• 📖 (Updated) Read Along Experience providing real-time text highlighting during playback (PDF/EPUB)
  • (New) Word-by-word highlighting uses word-by-word timestamps generated server-side with whisper.cpp (optional)
• 🧠 (New) Smart Sentence-Aware Narration merges sentences across pages/chapters for smoother TTS
• 🎧 (New) Reliable Audiobook Export in m4b/mp3, with resumable, chapter-based export and regeneration
• 🚀 (New) Optimized Next.js TTS Proxy with audio caching and optimized repeat playback
• 💾 Local-First Architecture stores documents and more in-browser with Dexie.js
• 🛜 Optional Server-side documents using backend /docstore for all users
• 🎨 Customizable Experience
  • 🎨 Multiple app theme options
  • ⚙️ Various TTS and document handling settings
  • And more ...

🐳 Docker Quick Start

Prerequisites

• Recent version of Docker installed on your machine
• A TTS API server (Kokoro-FastAPI, Orpheus-FastAPI, Deepinfra, OpenAI, etc.) running and accessible

Note: If you have good hardware, you can run Kokoro-FastAPI with Docker locally (see below).

1. 🐳 Start the Docker container:

docker run --name openreader-webui \
  --restart unless-stopped \
  -p 3003:3003 \
  -v openreader_docstore:/app/docstore \
  ghcr.io/richardr1126/openreader-webui:latest

(Optionally): Set the TTS API_BASE URL and/or API_KEY to be default for all devices

docker run --name openreader-webui \
  --restart unless-stopped \
  -e API_KEY=none \
  -e API_BASE=http://host.docker.internal:8880/v1 \
  -p 3003:3003 \
  -v openreader_docstore:/app/docstore \
  ghcr.io/richardr1126/openreader-webui:latest

Note: Requesting audio from the TTS API happens on the Next.js server not the client. So the base URL for the TTS API should be accessible and relative to the Next.js server. If it is in a Docker you may need to use host.docker.internal to access the host machine, instead of localhost.

Visit http://localhost:3003 to run the app and set your settings.

Note: The openreader_docstore volume is used to store server-side documents. You can mount a local directory instead. Or remove it if you don't need server-side documents.

2. ⚙️ Configure the app settings in the UI:

• Set the TTS Provider and Model in the Settings modal
• Set the TTS API Base URL and API Key if needed (more secure to set in env vars)
• Select your model's voice from the dropdown (voices try to be fetched from TTS Provider API)

3. ⬆️ Updating Docker Image

docker stop openreader-webui && \
docker rm openreader-webui && \
docker pull ghcr.io/richardr1126/openreader-webui:latest

🗣️ Local Kokoro-FastAPI Quick-start (CPU or GPU)

You can run the Kokoro TTS API server directly with Docker. We are not responsible for issues with Kokoro-FastAPI. For best performance, use an NVIDIA GPU (for GPU version) or Apple Silicon (for CPU version).

Docker CPU

docker run -d \
  --name kokoro-tts \
  --restart unless-stopped \
  -p 8880:8880 \
  -e ONNX_NUM_THREADS=8 \
  -e ONNX_INTER_OP_THREADS=4 \
  -e ONNX_EXECUTION_MODE=parallel \
  -e ONNX_OPTIMIZATION_LEVEL=all \
  -e ONNX_MEMORY_PATTERN=true \
  -e ONNX_ARENA_EXTEND_STRATEGY=kNextPowerOfTwo \
  -e API_LOG_LEVEL=DEBUG \
  ghcr.io/remsky/kokoro-fastapi-cpu:v0.2.4

Adjust environment variables as needed for your hardware and use case.

Docker GPU

docker run -d \
  --name kokoro-tts \
  --gpus all \
  --user 1001:1001 \
  --restart unless-stopped \
  -p 8880:8880 \
  -e USE_GPU=true \
  -e PYTHONUNBUFFERED=1 \
  -e API_LOG_LEVEL=DEBUG \
  ghcr.io/remsky/kokoro-fastapi-gpu:v0.2.4

Adjust environment variables as needed for your hardware and use case.

⚠️ Important Notes:

• For best results, set the -e API_BASE= for OpenReader's Docker to http://kokoro-tts:8880/v1
• For issues or support, see the Kokoro-FastAPI repository.
• The GPU version requires NVIDIA Docker support and works best with NVIDIA GPUs. The CPU version works best on Apple Silicon or modern x86 CPUs.

Local Development Installation

Prerequisites

• Node.js (recommended: use nvm)

• pnpm (recommended) or npm

  npm install -g pnpm

• A TTS API server (Kokoro-FastAPI, Orpheus-FastAPI, Deepinfra, OpenAI, etc.) running and accessible Optionally required for different features:

• FFmpeg (required for audiobook m4b creation only)

  brew install ffmpeg

• libreoffice (required for DOCX files)

  brew install libreoffice

• whisper.cpp (optional, required for word-by-word highlighting)

  # clone and build whisper.cpp (no model download needed – OpenReader handles that)
  git clone https://github.com/ggml-org/whisper.cpp.git
  cd whisper.cpp
  cmake -B build
  cmake --build build -j --config Release
  
  # point OpenReader to the compiled whisper-cli binary
  echo WHISPER_CPP_BIN=\"$(pwd)/build/bin/whisper-cli\"

  Note: The WHISPER_CPP_BIN path should be set in your .env file for OpenReader to use word-by-word highlighting features.

Steps

1. Clone the repository:

   git clone https://github.com/richardr1126/OpenReader-WebUI.git
   cd OpenReader-WebUI

2. Install dependencies:

   With pnpm (recommended):

   pnpm i # or npm i

3. Configure the environment:

   cp template.env .env
   # Edit .env with your configuration settings

   Note: The base URL for the TTS API should be accessible and relative to the Next.js server

4. Start the development server:

   With pnpm (recommended):

   pnpm dev # or npm run dev

   or build and run the production server:

   With pnpm:

   pnpm build # or npm run build
   pnpm start # or npm start

   Visit http://localhost:3003 to run the app.

💡 Feature requests

For feature requests or ideas you have for the project, please use the Discussions tab.

🙋‍♂️ Support and issues

If you encounter issues, please open an issue on GitHub following the template (which is very light).

👥 Contributing

Contributions are welcome! Fork the repository and submit a pull request with your changes.

❤️ Acknowledgements

This project would not be possible without standing on the shoulders of these giants:

• Kokoro-82M model
• Orpheus-TTS model
• Kokoro-FastAPI
• Orpheus-FastAPI
• react-pdf npm package
• react-reader npm package

Docker Supported Architectures

• linux/amd64 (x86_64)
• linux/arm64 (Apple Silicon, Raspberry Pi, SBCs, etc.)

Stack

• Framework: Next.js (React)
• Containerization: Docker
• Storage: Dexie + IndexedDB (in-browser local database)
• PDF:
  • react-pdf
  • pdf.js
• EPUB:
  • react-reader
  • epubjs
• Markdown/Text:
  • react-markdown
  • remark-gfm
• UI:
  • Tailwind CSS
  • Headless UI
  • @tailwindcss/typography
• TTS: (tested on)
  • Deepinfra API (Kokoro-82M, Orpheus-3B, Sesame-1B)
  • Kokoro FastAPI TTS
  • Orpheus FastAPI TTS
• NLP: compromise NLP library for sentence splitting

License

This project is licensed under the MIT License.