OpenReader WebUI is a document reader with text-to-speech functionality that provides a TTS reading experience for EPUB, PDF, TXT, MD and DOCX documents with narration. It can use any OpenAI-compatible TTS endpoint, including the Kokoro-Fast API and Orpheus-Fast API. TTS API integration Supports OpenAI text-to-speech API and GPT-4o Mini TTS, Kokoro-FastAPI TTS, Orpheus FastAPI or any other compatible service Support text-to-speech models (tts-1, tts-1-hd, gpt-4o-mini-tts, kokoro and custom) Local-first architecture: Store documents using the IndexedDB browser 🛜Optional server-side documents: Manually upload documents to the next backend for all users to download Read-as-you-go experience: Follow the highlighted text and read it aloud in TTS Document format: EPUB, PDF, TXT, MD, DOCX (requires installation of libreoffice) Audio book creation: Create and export audio books from PDF and epub files (output using ffmpeg and aac TTS in m4b format) 📲Mobile support: Can be used on mobile devices and added as a PWA web application 🎨Customizable experience: Set the TTS API basic URL (optional API key) Set model-specific instructions for GPT-4o Mini TTS ˇAdjustable playback speed 📐Customize PDF text extraction margins ˇMultiple voice options (check/v1/audio/voices endpoints) 🎨Various application theme options openai-edge-tts has been integrated by default and is available out of the box
