Speech-to-Action

(speech to paste)

macOS menubar app for voice-to-text with OpenAI Whisper API.

Press ⌃⌥A (control+option+A) anywhere to transcribe speech into focused app.

Demo

CleanShot.2025-11-10.at.08.36.47.mp4

Quick Start

Run the python in background:

git clone https://github.com/arealclimber/speech-to-action.git
cd macos_menubar_app
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
export OPENAI_API_KEY='your-openai-api-key'
python3 speech_to_clipboard.py

Features

• Global hotkey - Start/stop recording from anywhere
• Auto-paste - Text appears in focused app automatically
• Multi-language - Auto-detect or specify language

Requirements

• macOS 10.14+
• Python 3.8+
• OpenAI API key from platform.openai.com

Documentation

• README - Full documentation
• Quick Start - 2-minute setup guide

Tech Stack

• OpenAI Whisper API (speech-to-text)
• rumps (menubar framework)
• sounddevice (audio recording)
• pynput (global hotkey)
• pyperclip (clipboard)