On-device voice models for transcription and meetings on macOS.
Run 100% private speech-to-text and AI meeting summaries on Apple Silicon.
Ghost Pepper provides local speech-to-text and meeting transcription for macOS using Apple Silicon. It suits sales professionals and researchers handling sensitive client calls who need local data processing without cloud APIs.
The application listens via a global hotkey, transcribes audio locally through models like Whisper or Qwen, and cleans up filler words using a local LLM. It saves notes, transcripts, and AI summaries as markdown files directly on your Mac.
It suits macOS users needing private, offline transcription for prospect calls and meetings. It does not suit Windows or Linux users, or those without Apple Silicon hardware.
Release to transcribe and paste speech into any active text field.
Removes filler words and self-corrections using an on-device language model.
Saves call notes, transcripts, and summaries as markdown files on disk.
Runs quietly in the menu bar with no dock icon and launches at login.
Ghost Pepper is free and open source under the MIT license. The only cost is running it yourself on compatible Apple Silicon hardware.
896 open remote AI-training roles, updated November 16, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.
These reviewed AI tools do the same job instantly — from our scored directory.
No, all speech-to-text, text cleanup, and meeting summaries run entirely on your Mac.
You need a Mac running macOS 14.0+ with Apple Silicon (M1 or newer).
See Zekai first in Google