Fluentry is a local voice-to-text dictation tool for Linux and Wayland that runs speech recognition models on your machine without uploading data. It supports dozens of languages, integrates with PipeWire and system keyboards, and includes features like custom dictionary management, filler-word removal, and optional local grammar correction through language models.
AssemblyAI is open-sourcing Blurt, a dictation app that transcribes audio in ~150ms and cleans text in under a second using their Dictation API. It supports 19 languages with code-switching, offers customizable output styles, and achieves up to 30% fewer hallucinations than Whisper.
Karen is a development-only React overlay that lets developers point at app components, speak or type feedback, and automatically package it with component names, source locations, and screenshots for AI coding agents to act on. The tool integrates with React Grab for component lookup and supports voice transcription via browser speech or local Whisper models.
VideoHighlighter is a free, self-hosted desktop tool that analyzes video offline to identify and export highlight reels by scoring moments across scene, motion, audio, objects, actions, and transcripts. It features explainable AI with detailed reports showing the arithmetic behind each kept moment, composition rules for custom detection combinations, and supports batch processing with music synchronization and blur filtering.