Open-source alternatives to Readest

ReadYou is a self-hosted reading application and RSS feed aggregator that centralizes content from multiple web sources. It functions as a full-text RSS reader, extracting the complete body text from web pages to provide a distraction-free reading experience. The application includes specialized accessibility and speed tools, such as a bionic reading mode that uses pattern-based text highlighting to guide the eye and a text-to-speech system for audio content consumption. The project covers comprehensive subscription management through OPML import and export, feed categorization, and keyword-

This project is a framework for developing multimodal AI agents that function as programmable participants in real-time communication rooms. It enables the construction of agents that can see, hear, and speak by integrating speech-to-text, large language models, and text-to-speech pipelines to facilitate low-latency, natural conversations. The system is distinguished by its advanced orchestration of real-time media and conversational flow, including support for full-duplex speech, preemptive response generation, and sophisticated interruption management. It further differentiates itself throu

Zulip is an open-source, self-hosted chat platform designed for real-time team communication. It organizes conversations into threaded streams, allowing users to maintain focus and manage complex discussions within a private, secure infrastructure. The project provides full control over data, authentication, and server management, making it a comprehensive solution for organizations requiring a dedicated messaging environment. The platform distinguishes itself through a hybrid backend architecture that combines a robust web framework for standard requests with an asynchronous event-streaming

anx-reader is a cross-platform e-book reader and cloud-synced library manager. It renders various electronic book formats into a standardized HTML view with customizable themes and fonts for a consistent experience across different operating systems. The project integrates a large language model as a reading assistant to summarize text and answer questions about book content. It also functions as a digital annotation tool for creating color-coded highlights and detailed notes for external research export. The system includes capabilities for organizing digital library collections, synchroniz

BookReader is a mobile e-book reader application designed for reading digital novels in EPUB, PDF, and TXT formats. It functions as a digital library manager for organizing, indexing, and searching collections of electronic books using titles and tags. The application features a reading interface with three-dimensional page-flip animations to simulate the feel of physical books. It also includes a wireless synchronization system for transferring digital book files between devices over a local network. The software provides tools for customizing the reading experience, including adjustable th

OpenVoice is a multilingual text-to-speech framework and voice cloning AI model designed for high-fidelity voice replication and low-latency audio generation. It functions as an instant speech synthesis engine that converts text to audio while replicating a specific speaker's tone and color. The system is distinguished by its ability to perform cross-lingual cloning, allowing the vocal characteristics of a reference speaker to be applied to speech in different languages regardless of the original training data. It utilizes a decoupled representation to separate the physical identity of a voic

This Python SDK provides a comprehensive toolkit for synthetic audio generation, voice cloning, and the development of conversational AI agents. It enables the creation of lifelike spoken audio from text, the replication of human voices through custom cloning, and the deployment of real-time voice agents capable of interacting with external large language models. The library distinguishes itself through deep integration of conversational AI capabilities, including the design of agent personas and the execution of real-time actions via APIs. It supports professional-grade audio production thro

F5-TTS is a text-to-speech system that utilizes a flow matching engine and diffusion transformers to generate fluent synthetic speech. It functions as a multilingual speech synthesizer and neural training framework, providing tools for voice cloning and high-performance inference serving. The project distinguishes itself through a voice cloning toolkit capable of mimicking specific speaker characteristics and tones from reference audio clips. It supports cross-lingual generation, allowing for the synthesis of audio across various global languages or the mixing of multiple languages within a s

Nextra is a documentation framework for Next.js that functions as an MDX static site generator. It enables the creation of structured technical documentation sites by transforming MDX files into themed static pages with built-in layout and navigation. It serves as a React-based documentation tool that allows the integration of custom React components directly into markdown content. The framework distinguishes itself through integrated full-text search and a localization system that manages multilingual content via language routing and translation selectors. It also includes an AI-powered chat

ChatTTS is a conversational text-to-speech generative model designed to convert written dialogue into natural sounding audio. It functions as a multilingual speech synthesis framework capable of producing human-like audio across different languages and speaker profiles. The system is distinguished by its ability to generate interactive dialogue with realistic vocal nuances. It utilizes a speech nuance controller to insert specific tokens that trigger non-verbal elements, such as laughter, pauses, and interjections, during the synthesis process. The project includes a streaming audio generato

This project is a deep learning text-to-speech toolkit used for training and deploying neural speech synthesis models. It provides a comprehensive framework for converting written text into spoken audio, utilizing neural vocoders to transform synthesized spectrograms into high-fidelity audio waveforms. The toolkit includes a voice cloning system that replicates specific human voices by extracting speaker embeddings from short audio samples. It also supports multi-speaker audio synthesis, allowing the generation of speech across different vocal identities using specialized model architectures.

Sherpa-ONNX is an ONNX-based speech processing toolkit that provides a local speech recognition engine, an on-device voice synthesis tool, and a speaker identification framework. It is designed as a cross-platform speech API that enables speech-to-text, text-to-speech, and speaker verification tasks to be executed locally on a device without requiring network access. The project is distinguished by its ability to perform zero-shot voice cloning and speaker diarization on-device. It supports a wide range of hardware accelerations, including GPU and various NPU architectures, and provides a Web

This project is a generative speech synthesis engine that converts text into high-fidelity human speech. It utilizes a two-stage autoregressive transformer architecture that separates semantic token prediction from acoustic detail reconstruction to balance linguistic accuracy with audio quality. The system is designed to support multilingual output and conversational AI development, enabling the generation of context-aware speech that maintains flow across multiple dialogue turns. The platform distinguishes itself through a production-ready inference server that employs continuous batching to

Podcastfy is an AI content-to-podcast generator that converts text, URLs, PDFs, images, and videos into conversational audio podcasts. It integrates with over 100 language models for transcript creation and multiple text-to-speech engines for audio output, with support for customizable dialogue style and optional local transcript generation for privacy. The project distinguishes itself through a flexible architecture that decouples job submission from result retrieval via asynchronous polling, normalizes heterogeneous inputs into uniform text, and routes content through pluggable LLM and TTS

Librum is a cross-platform digital ebook reader and library manager designed to render multiple book formats. It functions as an integrated reading assistant and a system for organizing digital libraries across multiple devices. The project distinguishes itself by providing a self-hosted backend option, allowing users to maintain full control over their book data and metadata via a private server. It also integrates a language model assistant to provide text summarization, explanations, and translations of specific passages while reading. The application covers comprehensive library manageme

TranslationPlugin is a translation utility for IntelliJ-based editors and Android Studio. It functions as a multi-engine translation tool that converts selected text, code symbols, and entire documents into target languages. The project integrates a personal lexicon and word book for saving translated terms to facilitate vocabulary study. It also includes a text-to-speech interface that reads translated text aloud to provide audio pronunciation of foreign words. The plugin covers a range of translation and localization capabilities, including the conversion of documentation and rendered view

Breezy Weather is an open-source weather forecast application and data visualizer. It serves as a mobile client that retrieves atmospheric data, air quality forecasts, and UV indices from various open-source or self-hosted weather service endpoints using REST API integration. The application features a customizable interface that supports the scanning of third-party icon packs, live wallpapers, and home screen widgets. It includes location-based reporting via GPS coordinates or manually selected cities, with options for location privacy management through IP-based masking to reduce coordinate

Docsify is a client-side documentation framework and no-build static site generator. It functions as a browser-based engine that converts Markdown files into HTML on the fly, allowing for the generation of documentation websites without a static build or compilation process. The system employs a plugin interface and lifecycle hooks to modify the rendering process and extend site capabilities. It supports dynamic theme injection and visual style customization through external CSS and layout configurations. The framework includes capabilities for multi-language content management, full-text se

LiveKit is a comprehensive framework for building and orchestrating real-time, multimodal AI agents that interact with users through voice, video, and text. It provides a centralized, event-driven architecture to manage the entire lifecycle of automated participants, from initialization and session state management to graceful shutdown. By utilizing a selective forwarding unit, the platform efficiently routes media streams between participants and agents, ensuring low-latency communication and secure, token-based authentication for all connections. The platform distinguishes itself through it

Caprine is a privacy-focused desktop client for Facebook Messenger. It functions as an Electron-based wrapper that encapsulates the web application to provide system-level features and advanced user interface customizations. The client prioritizes user privacy by masking activity status, hiding typing indicators, and blocking tracking parameters from outgoing links. It further enhances the user experience through a customizable interface that supports dark mode, custom stylesheets, and window vibrancy effects. The application includes tools for keyboard-driven navigation to switch between co

Platform is a framework for building back-office applications and administrative dashboards using Laravel. It functions as a schema-driven UI framework and CRUD generator that automatically constructs database management interfaces, input forms, and validation rules from programmatic model definitions. The project distinguishes itself through a comprehensive backend UI kit that supports advanced data capture, including geographic coordinate mapping, tabular JSON data matrices, and marketing metadata tracking. It features a robust role-based access control system for managing resource visibili

Paperless is a self-hosted document management system designed to digitize, index, and archive paper documents. It functions as an optical character recognition system that converts scanned images and PDFs into a searchable digital library, providing a web-based interface for querying and retrieving documents from a database. The system features an automated file ingestion pipeline that monitors specific directories and email inboxes to process and import documents without manual uploading. To maintain a private archive, it includes on-disk encryption for sensitive files and the ability to or

Calibre-web is a self-hosted web application that provides a browser-based interface for browsing, managing, and reading digital book collections stored in a library database. It functions as a comprehensive library management system, allowing users to organize large collections, edit metadata, and perform automated content updates through a centralized administrative dashboard. The platform distinguishes itself by integrating directly with external infrastructure to extend the capabilities of a standard digital library. It supports remote storage mapping to host files on cloud providers, uti

FreshRSS is an open-source, self-hosted web feed aggregator designed to collect, organize, and display content from multiple websites in a single, centralized interface. It functions as a comprehensive reader for standard syndication formats, allowing users to track updates from various sources while maintaining full control over their data and privacy. The platform supports multi-user environments, enabling individual account management and personalized reading experiences. The application distinguishes itself through its robust synchronization and extensibility capabilities. It provides a s

Vditor is a browser-based Markdown editor and rendering engine that supports multiple editing interfaces, including a visual rich-text experience, instant rendering, and a traditional side-by-side split-view preview. It serves as an authoring tool for technical documentation and a component for web-based editor integration. The project is distinguished by its support for complex technical content, utilizing specialized rendering for mathematical formulas, flowcharts, sequence diagrams, and mind maps. It also functions as a collaborative document review tool, enabling users to attach anchored

This repository contains a collection of extensions and configurations for a text editor plugin ecosystem. It provides a framework for adding language support and custom behavior through a system of customizable key bindings, a project indexing engine, and a syntax highlighting framework. The project utilizes a Python API to enable the development of custom plugins, menus, and tools. It supports a functional extension framework where users can create custom themes, syntax definitions, and resource overrides to expand the editor's visual styles and capabilities. The system covers advanced tex

jless is an interactive JSON explorer and command-line viewer designed for reading and navigating hierarchical data structures within a terminal. It functions as a terminal JSON formatter that pretty-prints data from files or standard input, including support for newline-delimited formats. The tool serves as a JSON path extractor, allowing users to identify and copy the dot or bracket notation paths from the root to specific nodes. It also includes a regex search utility for locating specific keys and values within JSON datasets using full-text regular expressions. The application provides c