OpenReader
Open-source text-to-speech document reader with read-along narration for EPUB, PDF, TXT,MD
OpenReader is an open-source text-to-speech document reader built with Next.js that provides a multilingual read-along experience with narration for EPUB, PDF, TXT, MD, and DOCX documents. It was previously named OpenReader-WebUI. The tool addresses the need to listen to and follow along with documents through synchronized audio and highlighting.
Key features include progressive background generation and playback, layout-aware PDF parsing using PP-DocLayoutV3 (ONNX), word-by-word highlighting via ONNX Whisper alignment, and a NATS JetStream-backed compute worker control plane. It supports multiple TTS providers: self-hosted options such as Kokoro-FastAPI, KittenTTS-FastAPI, and Orpheus-FastAPI, plus cloud providers including OpenAI, Replicate, and DeepInfra, along with custom OpenAI-compatible endpoints. Additional capabilities include audiobook export in M4B or MP3, flexible backend storage with embedded SeaweedFS or S3-compatible options, SQLite or Postgres databases, server library import, device sync, authentication with optional anonymous sessions, and 13 built-in themes with per-user TTS settings.
OpenReader is available as open-source software distributed via GitHub, with documentation covering Docker Compose deployment, local development, and Vercel deployment.
12 alternatives to OpenReader
Ranked by how well each tool replaces OpenReader: shared features, audience, price and popularity.
- 67 out of 100 matchContact sales
Listen to text aloud, use voice typing, and get fast answers with Speechify — Voice AI
Covers 4 of 15 key features.
Free plan61 out of 100 match$29/moText to Speech Software for Windows that converts documents, webpages and PDF files into a
Covers 5 of 15 key features.
59 out of 100 match—Studio-grade AI text-to-speech and voice cloning with emotion control and a large voice
Covers 4 of 15 key features.
Free plan58 out of 100 match$11/mo- 58 out of 100 match$2/mo
AI voice platform for text-to-speech, dubbing, and conversational voice agents
Covers 3 of 15 key features.
Free plan58 out of 100 matchContact salesSpeech-to-text, text-to-speech and voice agent APIs for real-time and batch audio, usable
Covers 1 of 15 key features.
Free plan57 out of 100 matchUsage-basedTranscription and conversion of audio and video into text
Covers 7 of 15 key features.
Free plan57 out of 100 matchContact sales- 57 out of 100 match$1.90/mo
Speech-to-text and speech understanding APIs for voice AI applications
Covers 2 of 15 key features.
Free plan56 out of 100 matchContact salesPowerful Speech Platform – Text to Speech API, Speech Recognition API, Open Source SDKs
Covers 3 of 15 key features.
Free plan56 out of 100 matchUsage-based