Open Source Input & Dictation Software
Input & Dictation software converts spoken language into written text for use in active documents and text fields. These tools transcribe voice recordings or live speech into notes, meeting summaries, and structured prompts. This type of software serves writers and professionals who need to digitize audio without sending voice recordings to external servers. By hosting these apps locally, you keep audio files and transcribed text on your own hardware. This approach ensures that sensitive conversations and private voice memos remain offline and away from corporate cloud storage.
This page lists 9 open source tools in the Input & Dictation category. The most popular are Handy, Meetily and Vibe. Most use the MIT or GPL-3.0 license, and 1 offers an official Docker image.
Handy
Transcribes voice into any active text field using local processing and configurable keyboard shortcuts.
Meetily
Records, transcribes, and summarizes meetings on local infrastructure to maintain data sovereignty and privacy.
Vibe
Convert audio and video files into text offline using the OpenAI Whisper model on desktop devices.
VoiceInk
A native macOS application that transcribes speech to text locally using AI for private voice dictation.
OpenWispr
Convert voice to text and notes using local or cloud transcription engines across multiple desktop platforms.
OpenLess
Convert spoken language into polished text or structured AI prompts inserted directly at the system cursor.
Amical
Local AI dictation and note taking software that formats speech to text based on the active application.
Minutes
Records meetings and voice memos locally to create a queryable markdown archive for AI agents.
Jarvis
A macOS voice assistant that transcribes speech into text and applies AI transformations across any application.
Join our newsletter to get shiny new open source software delivered to your inbox. Unsubscribe anytime.