Hex

Hex

Transcribes spoken audio into text locally on your device and pastes the output into active applications. This tool is for users who want private speech recognition without sending audio data to a cloud service.

Made by anomalyco on GitHub. These notes are Minda's, written from its README; the project's own files and license are in its repository.

About

What it is: Hex provides local voice dictation for macOS, Windows, and Linux. It transcribes audio on your device and pastes the result into your active application.

How to set it up: You can install the software using your operating system installer or a package manager.

brew install --cask anomalyco/tap/hex

yay -S hex-bin

nix profile add github:anomalyco/hex

How to use it: You hold the shortcut key, speak, and release the key to paste the text. You can find experimental features in the Labs section at the bottom of the sidebar.

For newcomers and experts: You may use this tool to dictate text directly into your applications. It keeps your data on your machine after the first run downloads the required speech model.

Good to know:

• Holds audio data on your device.
• Downloads a speech model on the first run.
• Supports macOS, Windows, and Linux.
• MIT licensed.

On GitHub, 4 November 2026

• Stars: 4,620 (410 that day)
• Forks: 259
• Watching: 8
• Open issues and pull requests: 124
• Language: Rust
• License: MIT
• Topics: dictation, linux, local-first, macos, rust, speech-recognition, speech-to-text, voice-control
• Trending: #10 repository of the day on GitHub trending (4 November 2026)

Links

• Code: https://github.com/anomalyco/hex
• Website: https://anoma.ly/hex
• Releases: https://github.com/anomalyco/hex/releases
• Issues: https://github.com/anomalyco/hex/issues
• Star history: https://www.star-history.com/#anomalyco/hex&Date

Get the code

git clone https://github.com/anomalyco/hex.git

Then follow the setup in its README. Nothing in this kit runs by itself.