Find tools › Open-source projects › Images, video & voice

hex

Open-source project · by anomalyco

A desktop app that turns your spoken voice into text and pastes it into any open window.

No codingWell known

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Dictate text directly into any open application using a global hotkey
  • Transcribe your voice completely offline using on-device speech models
  • Record screen annotations and spoken instructions to share with agents

How to start

  1. Install the app via brew install --cask anomalyco/tap/hex or download the installer for your operating system.

  2. Launch Hex and grant the requested microphone and accessibility permissions.

  3. Download your preferred local speech transcription model in settings.

  4. Hold the Option key, speak your thoughts, and release to paste the transcribed text.

Good to know. Downloading local models requires access to Hugging Face, and enabling optional OpenCode text rewriting will send your transcript and window context to external providers.

Before you install

  • Found automaticallyNot reviewed by a person yet. Check it before installing.
  • License: MITYou are allowed to use it under these terms.
  • Last updated 2026-11-18

More detail

Hex is a local-first voice dictation app for desktop operating systems that transcribes your speech on-device and pastes it into whatever app you are using.

It replaces cloud-based dictation services with fast, private on-device speech models whenever you want to type with your voice without sending audio off your machine.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-11-01. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map