Back to Catalog
OpenReader logo

OpenReader

Self-hosted text-to-speech document reader with synchronized highlighting

app

Alternative to: speechify, natural reader, elevenlabs reader

Repository Docs
About Versions (51)
Back to Versions

v0.4.0

2025-11-09

What’s New

🎯 Multi-Provider TTS Support

Choose your preferred TTS provider:

  • OpenAI - Original provider
  • Deepinfra - Open-source models (Kokoro-82M, Orpheus-3B, Sesame-1B)
  • Custom OpenAI-Compatible - Self-hosted or third-party endpoints

Provider-specific voice management with automatic restoration per model.

📦 Package Manager Migration

Migrated to pnpm for improved dependency handling and reproducible builds.

🐳 Docker Improvements

Updated Docker configuration with Deepinfra API defaults and added docker-compose example with Kokoro-FastAPI integration.

🔧 Bug Fixes & Improvements

  • Documentation updates
  • CI/CD workflow improvements for pnpm

⚠️ Breaking Changes

Voice selection is now provider-model specific. Previously saved voices may need to be reselected.

Full Changelog

https://github.com/richardr1126/OpenReader-WebUI/compare/v0.3.3…v0.4.0

Changelog on GitHub →