Free & Open Source · macOS & Windows

Press a hotkey. Speak.
Text appears — anywhere.

An AI voice input that actually gets you — technical jargon, slang, code snippets, mixed languages. Far more accurate than Mac’s built-in dictation. Works in every app. Open source.

$ brew install --cask tyun08/tap/audio-input

Everything you need.
Nothing you don’t.

Built to stay out of your way. Invoke it, speak, and get back to work.

Works Everywhere

Injects text directly into any focused input. macOS Accessibility API and Windows key simulation. Slack, Notion, Terminal, browsers — anywhere.

AI That Gets Your Vocabulary

Understands domain jargon, slang, and mixed-language speech that trips up Mac’s built-in dictation. An optional LLM pass also removes filler words and fixes punctuation. Screenshot context makes it even smarter.

Multi-Provider

Groq Whisper (free API key) or Google Vertex AI Gemini (enterprise ADC). Switch providers with one click. Extensible to new providers.

Privacy First

Audio goes directly to your chosen provider — no intermediary server. Fully open source, BYOK. You own your data.

50+ Languages

Whisper large-v3-turbo and Gemini handle Chinese, English, Japanese, Korean, Spanish, and many more — auto-detected.

Featherweight

~20 MB RAM. Built with Tauri + Rust. No Electron, no background bloat. It just sits in your menu bar.

Your cloud, your choice

Switch providers any time. Adding a new one takes 3 files.

Groq
Free API Key
  • Whisper large-v3-turbo transcription
  • LLaMA-based AI polish
  • Free tier — generous for daily use
  • Sign up at console.groq.com
Vertex AI
Google Cloud
  • Gemini 2.5 Flash / Pro transcription
  • Multimodal polish with screenshot context
  • No API key — uses gcloud ADC
  • Enterprise-grade for teams already on GCP

One command
to get started

Install via Homebrew on macOS, or grab the installer from GitHub Releases for macOS & Windows.

Terminal
$ brew install --cask tyun08/tap/audio-input

Prefer a manual download? GitHub Releases →

Windows: Download the .msi installer from Releases. Windows 10+ required.

Up and running in 3 steps

Pick a provider and start talking.

1

Get a free Groq API key

Sign up at console.groq.com. The free tier is generous enough for daily use.

2

Paste your key in the app

Launch Audio Input, select Groq as your provider, and paste the API key. Done.

3

Press ⌘⇧Space and speak

Hold the hotkey, dictate, release. Your words appear at the cursor — polished and ready.