moona3k/macparakeet

Fast, private, local-first voice app for Apple Silicon Macs — dictation, file/media transcription, meeting recording, Transforms, and a public automation CLI. Free and open-source.

What it solves

MacParakeet is a local-first voice application for Apple Silicon Macs that provides a private and fast way to handle system-wide dictation, media transcription, and meeting recording without relying on cloud processing for speech recognition.

How it works

The app uses several local speech-to-text (STT) engines, with Parakeet (via FluidAudio CoreML) as the standard default. It also supports optional local models like Nemotron, Cohere Transcribe, and WhisperKit for different language or accuracy needs. It integrates with macOS EventKit to read calendar meetings for reminders and auto-start recording. For advanced automation, it provides a CLI (macparakeet-cli) that allows users to script transcriptions, manage models, and handle prompts.

Who it’s for

Users of Apple Silicon Macs (M1 or newer) who need high-performance, private voice-to-text tools for daily dictation, transcribing audio/video files (including YouTube and podcasts), or recording and summarizing meetings.

Highlights

  • Local-First Privacy: All speech recognition happens on-device; networked AI features for summaries or chat are entirely opt-in.
  • Versatile Transcription: Supports dragging and dropping files, pasting URLs from platforms like YouTube, X, and TikTok, or searching for podcasts via the iTunes API.
  • Meeting Integration: Records system audio and microphone simultaneously, provides live transcript previews, and integrates with the macOS Calendar for automated recording.
  • Extensible Automation: A dedicated CLI enables agent-based automation, allowing for scriptable transcription and prompt management.
  • Multiple Engine Support: Offers a variety of local engines (Parakeet, WhisperKit, Cohere, Nemotron) to balance speed, memory usage, and accuracy.

Related

  • Project
    ideaplexa/voicetypr

    Voicetypr is an open‑source, offline‑first dictation app for macOS and Windows. It captures speech via a global hot‑key, transcribes locally with Whisper (and Parakeet on Apple Silicon) or optionally via cloud STT services, can clean up the text with LLMs, and inserts the result at the current cursor. A companion CLI lets scripts or AI agents use the same transcription pipeline, returning plain text or JSON. The app is built with Tauri (Rust backend) and React, offers LAN‑based private transcription servers, and is released under AGPL‑3.0.

  • Project
    altic-dev/FluidVoice

    An open-source voice-to-text dictation app for macOS that provides on-device AI enhancement and system control via voice.

  • Project
    Muesli-HQ/muesli

    Muesli is a native macOS app for on‑device dictation and meeting transcription, with optional cloud LLM summarisation and an agent‑friendly CLI.

  • Project
    Beingpax/VoiceInk

    VoiceInk is a macOS‑only, offline speech‑to‑text app that uses local Whisper‑based models (via whisper.cpp and transcribe‑cpp‑swift) to provide near‑instant, privacy‑preserving transcription, context‑aware modes, custom dictionaries, global shortcuts, and a built‑in AI assistant. It’s open‑source under GPL‑v3, installable via Homebrew or from source, with optional paid licensing for updates and support.

  • Project
    TypeWhisper/typewhisper-mac

    A system-wide speech-to-text and AI text processing utility for macOS that supports local and cloud transcription engines with customizable AI workflows.