What can I use Handy for?

Hold your shortcut in a chat app and speak a sentence, and the transcribed text is pasted into the message box. Run the command-line toggle flag from a script, and you start or stop recording without touching the Handy window. Put an executable transcription hook in Handy's app data folder on macOS, and dictated text gets a # prefix whenever Terminal is the frontmost app.

What do I need to use Handy?

A Windows, macOS or Linux computer, with microphone and accessibility permissions granted. Whisper models can use GPU acceleration when available, and Parakeet V3 is CPU-optimized. Memory needs are not documented.

Handy: Dictate into any text field with offline speech-to-text

What it does

Handy is a free, open-source cross-platform desktop app for speech-to-text. You hold or tap a keyboard shortcut and speak. It filters out silence, transcribes with a Whisper or Parakeet V3 model on your own computer, and pastes the text into the app you are using.

How to use it

Download the latest release from the project's releases page or the Handy website and install it. On macOS you can use Homebrew, and on Windows winget, though the developers do not maintain those packages. On Debian or Ubuntu, install the downloaded .deb with APT. Launch Handy, grant microphone and accessibility permissions, set your shortcuts in Settings, and start talking.

Common use cases

Hold your shortcut in a chat app and speak a sentence, and the transcribed text is pasted into the message box.
Run the command-line toggle flag from a script, and you start or stop recording without touching the Handy window.
Put an executable transcription hook in Handy's app data folder on macOS, and dictated text gets a # prefix whenever Terminal is the frontmost app.

Can I use this?

Mac, Windows or Linux app

Requirements It runs on your own computer: Windows, macOS or Linux. Download and install it, then allow microphone and accessibility access. Licensed under MIT.

Caveat The project is under active development with known issues, and the transcription hook is documented only for macOS and Linux.

Worth knowing On macOS, a Bluetooth headset microphone can reduce playback quality while recording, and shortcuts that use the fn key only work on Apple keyboards.

Why it's here

2,169 people starred it on GitHub this week — 38,011 in total.

Numbers as of 8 November 2026, from BuildTube’s latest daily refresh.

Behind it

View setup guide

BuildTube has not run or verified this project. Everything above is written from what the creator published.

Made this?

Quick questions

What is Handy?: Handy is a free, open-source cross-platform desktop app for speech-to-text.
What can I use Handy for?: Hold your shortcut in a chat app and speak a sentence, and the transcribed text is pasted into the message box. Run the command-line toggle flag from a script, and you start or stop recording without touching the Handy window. Put an executable transcription hook in Handy's app data folder on macOS, and dictated text gets a # prefix whenever Terminal is the frontmost app.
Can I run Handy on my computer?: It installs as a desktop app on your own computer (Windows, macOS or Linux). The project is under active development with known issues, and the transcription hook is documented only for macOS and Linux. On macOS, a Bluetooth headset microphone can reduce playback quality while recording, and shortcuts that use the fn key only work on Apple keyboards.
What do I need to use Handy?: A Windows, macOS or Linux computer, with microphone and accessibility permissions granted. Whisper models can use GPU acceleration when available, and Parakeet V3 is CPU-optimized. Memory needs are not documented.
What license does Handy use?: Licensed under MIT.

More from this week

agent-desktop Let AI agents read and click desktop apps
For developers building computer-use agents: agent-desktop lets an AI agent read and operate desktop apps on Mac, Windows or Linux from a command line.
+13,858 stars this weekAdded 3 Nov
Auto-Ontology Give AI agents checked business meanings for your database
Help AI agents answer questions about company databases using reviewed definitions and SQL, with each answer showing its steps.
+9,044 stars this weekNeeds a local setupAdded 4 Nov
Spec Kit Turn a written spec into plans, tasks and code
Spec Kit gives your AI coding agent a step-by-step process to build a feature, fix a bug or assess an idea.
+4,280 stars this weekAdded 2 Nov

Related projects

OpenWhispr Turn your voice into text with a hotkey
Same topic: cross-platform
Desktop appAdded 29 Oct
agent-desktop Let AI agents read and click desktop apps
Same topic: accessibility
+13,858 stars this weekAdded 3 Nov
NVIDIA-Nemotron-3.5-Transcribe-30B-A4B Transcribe hour-long recordings (34B)
Same topic: speech-to-text
Needs a model setupAdded 30 Oct
VoiceStudio Clone your voice and dub a video, all on your own computer
Same topic: speech-to-text
Desktop appAdded 25 Sept
Hex Dictate by voice and paste text into any app
Same topic: speech-to-text
Added 1 Nov
ux-ui-agent-skills Get accessible, consistent screen designs from Claude
Same topic: accessibility
Added 21 Oct

Explore by topic

Post this

For makers

Made this? Show it’s on BuildTube — add the badge to your README or embed the card on your site.

README badge (Markdown)

[![Featured on BuildTube](https://buildtube.app/badge/gh-cjpais-handy.svg)](https://buildtube.app/p/gh-cjpais-handy/)

Embed card (HTML)

<iframe src="https://buildtube.app/embed/gh-cjpais-handy/" width="560" height="240" style="border:0;max-width:100%" loading="lazy" title="Handy on BuildTube"></iframe>