Loading...
Loading...
Hex: Local-first voice dictation for macOS. It is listed under Productivity on AI Registry as a free tool.
The tools below are approved listings in the same category, ordered by how closely their tags match Hex. This is an automatic list. We have not written a researched verdict for Hex yet, so treat it as a shortlist and check each vendor's pricing page before switching.
Built from each tool's listing. Vendors can update their own listing after claiming it.
Muesli: agent-native local meeting transcription + dictation for macOS (Granola + WisprFlow alternative)
Muesli is an open source Mac app for dictation and meeting transcription that runs speech to text on the device. It targets Apple Silicon Macs and uses local speech models, with Parakeet and Whisper named on the site, so audio does not have to be uploaded to a cloud service. From the menu bar, the user holds a hotkey,...
Local, private voice dictation for macOS
Open Wispr is a free voice dictation tool for macOS that transcribes speech entirely on the user's own Mac. The user holds a key, speaks, and releases it, and the transcribed text is typed at the cursor in whatever app has focus, including editors, browsers, terminals, Slack and email. Transcription uses whisper.cpp w...
Free, open-source offline voice dictation for Windows, macOS, and Linux.
SpeakoFlow is a free, open source voice dictation and AI assistant for desktop. A user holds a key and talks, and the words are typed into whatever app has focus, including Slack, Gmail, ChatGPT, Notion, Cursor, Google Docs, Claude, Discord and Obsidian. It supports up to 99 languages and offers both live transcription...
Privacy-first voice dictation for macOS — powered by on-device Whisper AI.
Wispr is a voice dictation and meeting transcription app for macOS. The user presses Option+Space in any application, speaks, and releases the key, and the transcribed text appears at the cursor. The hotkey can be changed. All processing happens on the Mac using on device models, including Whisper and NVIDIA Parakeet,...
Voice AI runtime. Local first transcription, speaker diarization, TTS, and voice cloning with an OpenAI compatible API.
Izwi is a local first audio inference engine for speech, voice and chat workflows. It runs entirely on the user's own machine, so there are no cloud services, no API keys and no data leaving the device. The listing points to its user documentation site. The documented capabilities cover a broad set of audio tasks. Voi...
Capture first. Organize later.
NoteGen is an open source, cross platform AI note taking app built around the idea of capturing first and organizing later. It stores notes as plain Markdown files, so they can sync across devices through services such as OneDrive or iCloud Drive. Everything enters one stream of records: text, voice, screenshots, imag...