WhisperShortcut icon

WhisperShortcut

Speech-to-text and AI voice commands with Google Gemini or offline Whisper

Free DictationTranscription Open Source

Overview

WhisperShortcut is a macOS application that converts speech to text and voice commands into AI-powered text modifications using Google Gemini or offline Whisper technology. It transcribes audio via cloud (Gemini) or offline (Whisper) processing, processes voice instructions to modify clipboard text, and reads selected text aloud with AI voices. Features chunked transcription for long recordings with parallel processing.

Pricing: Free (GitHub) | Paid version on Mac App Store

Minimum macOS: 15.5 (Sequoia)

Architecture: Apple Silicon, Intel

Key Features

  • Cloud transcription via Google Gemini API
  • Offline privacy mode using local Whisper models
  • Chunked transcription for long recordings with parallel processing
  • Voice instructions to modify clipboard text
  • Text-to-speech with multiple AI voices
  • Customizable keyboard shortcuts for each mode
  • Real-time progress tracking for audio processing
  • Combined prompting and text-to-speech workflows

Tags

transcriptionvoice inputvoice synthesistext generation