AI BriefingOpenReader v3.0 Released
·2026.05.17 03:12
Key point
OpenReader v3.0, an open-source document reader that supports various AI TTS engines and can produce audiobooks, has been released.
Details
OpenReader is a Next.js-based open-source web application for reading and listening to EPUB, PDF, TXT, Markdown, and DOCX files.
Key Features and Highlights:
- Support for various TTS engines: Supports OpenAI, Replicate, Deepinfra, and self-hosted OpenAI-compatible APIs such as Kokoro-FastAPI and KittenTTS-FastAPI.
- Self-hosted: Documents, TTS audio, and settings data can be managed directly on your own server (SQLite, Postgres) and object storage (SeaweedFS, S3).
- Audiobook generation: Uses ffmpeg to create and download audiobooks in m4b/mp3 format with chapter metadata.
Key updates in v3.0.0:
- Audio preloading and caching: Preloads audio for the next page based on reading progress, and caches audio in the server's object storage to enable seamless playback.
- Introduction of an admin panel: Allows management of API keys for multiple TTS providers and control of feature flags (user sign-up, provider restrictions, etc.) at runtime without redeploying the service.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Jevper Released: A Jev Classification Wrapper for OpenAI-Compatible Models with Automatic Logprobs Detection
Rootless Linux Sandbox 'Drop' Released for Isolating AI Agents and Third-Party Programs