Fast voice app for Mac with fully local speech and optional AI. Free and open-source.
There are many voice transcription/dictation apps, but this one is mine.
MacParakeet runs NVIDIA's Parakeet TDT on Apple's Neural Engine via FluidAudio CoreML. The current stable release includes system-wide dictation, file/URL transcription, meeting recording, meeting calendar support, optional local WhisperKit recognition for languages Parakeet does not cover, and Transforms for selected-text rewrites. All speech recognition happens on your Mac.
The notarized DMG is the stable release channel.
| Channel | Status | Includes |
|---|---|---|
| Stable DMG | Recommended for normal use | Dictation, file/video/YouTube transcription, meeting recording, meeting calendar reminders and opt-in auto-start, Transforms, optional WhisperKit, exports, vocabulary, AI features |
main branch |
Development | Latest stable release plus in-progress fixes and development changes, including beta media pause while dictating |
Meeting calendar support is live in the stable DMG. MacParakeet reads upcoming meetings from the local macOS Calendar store through EventKit, can show reminders, and can optionally start a recording after a countdown. Auto-start defaults to .off and must be opted into; recordings still stop manually.
Dictation — Press a hotkey in any app, speak, text gets pasted. Hold for push-to-talk, or tap the hands-free shortcut to start and stop longer dictations. Works system-wide. A beta setting can pause supported Now Playing media while you dictate and resume it when capture stops.
File transcription — Drag audio or video files, or paste a YouTube URL. Full transcript with word-level timestamps, speaker labels, and export to 7 formats (TXT, Markdown, SRT, VTT, DOCX, PDF, JSON). Assign global hotkeys to trigger File or YouTube transcription from anywhere.
Meeting recording — Record system audio and microphone together, see a live local transcript preview, take notes during the call, then save the finalized transcript to the library with export, prompts, and chat.
Meeting calendar support — Grant Calendar access to get local reminders for upcoming meetings or opt into auto-start. MacParakeet uses calendars already configured in macOS Calendar through EventKit; it does not add Google or Microsoft sign-ins, and recordings still stop manually.
Text cleanup — Filler word removal, custom word replacements, text snippets with triggers. Deterministic pipeline, no LLM needed.
AI features — Optional summaries, chat, AI formatter, and Transforms for rewriting selected text through your configured provider. Connect any cloud provider (OpenAI, Anthropic, Gemini, OpenRouter), local runtime (Ollama, LM Studio), OpenAI-compatible endpoint, or CLI tool (Claude Code, Codex). Entirely opt-in.
- ~155x realtime — 60 min of audio in ~23 seconds
- ~2.5% word error rate (Parakeet TDT 0.6B-v3)
- ~66 MB working memory per active Parakeet inference slot
- 25 European languages with Parakeet auto-detection
- Optional local WhisperKit engine for Korean, Japanese, Chinese, and many other languages
- Apple Silicon only (M1/M2/M3/M4)
- Parakeet is best for English and supported European languages
- WhisperKit multilingual support requires a separate local model download before first use
Download: Grab the notarized DMG or visit macparakeet.com. Drag to Applications, done.
First launch downloads the speech model (~6 GB) plus speaker-detection assets (~130 MB). Everything works fully offline after that.
The DMG is the stable release.
Standalone CLI (Homebrew):
brew install moona3k/tap/macparakeet-cli
macparakeet-cli --version
macparakeet-cli health --jsonThe Homebrew formula installs the public macparakeet-cli surface plus
Homebrew-managed ffmpeg and yt-dlp. It shares the same local database and
model cache as the app.
Build from source:
git clone https://github.com/moona3k/macparakeet.git
cd macparakeet
swift test
scripts/dev/run_app.sh # build, sign, launchThe dev script creates a signed .app bundle so macOS grants mic and accessibility permissions. It disables target-level Xcode signing, then signs the finished bundle with the best available local identity. Override with MACPARAKEET_CODESIGN_IDENTITY="Your Identity" if needed.
CLI:
macparakeet-cli transcribe /path/to/audio.mp3
macparakeet-cli transcribe /path/to/audio.mp3 --format transcript --no-history
macparakeet-cli models download whisper-large-v3-v20240930-turbo-632MB
macparakeet-cli models list
macparakeet-cli models select parakeet
macparakeet-cli transcribe /path/to/korean.mp3 --engine whisper --language ko --format json
macparakeet-cli models status
macparakeet-cli historyUse --format transcript for transcript-only stdout in shell pipelines. Add
--no-history when you want a one-off transcription without saving a completed
row to MacParakeet history. models list and models select inspect or update
the shared speech default used by the app and --engine app-default. The
Whisper CLI commands above require a downloaded local WhisperKit model. When
developing from source, prefix the same commands with swift run.
| Layer | Choice |
|---|---|
| STT | Parakeet TDT 0.6B-v3 via FluidAudio CoreML (default) + optional local WhisperKit engine |
| STT orchestration | Shared runtime + explicit scheduler with a reserved dictation slot and a shared meeting/file slot; speech-engine routing and meeting-session pinning |
| Language | Swift 6.0 + SwiftUI |
| Database | SQLite via GRDB |
| Auto-updates | Sparkle 2 |
| YouTube | yt-dlp |
| Platform | macOS 14.2+, Apple Silicon |
The Vocabulary panel controls how dictated text is cleaned up before pasting. No AI involved — it's a fast, deterministic pipeline that runs in under 1ms.
You choose between two processing modes:
- Raw — Paste exactly what the speech engine produces, no changes
- Clean (default) — Run the text through a multi-step pipeline before pasting
The Clean pipeline applies these steps in order:
- Filler removal — Strips "um", "uh", and sentence-start fillers like "so", "well", "like"
- Custom words — Applies your word replacement rules (e.g., "aye pee eye" becomes "API", or "kubernetes" gets capitalized to "Kubernetes"). Case-insensitive, whole-word matching. Words can be toggled on/off without deleting.
- Voice Return — If you've defined a trigger phrase (e.g., "press return") and speak it at the end of a dictation, it's stripped from the output and a Return keypress is simulated after paste
- Snippet expansion — Replaces short trigger phrases with longer text (e.g., "my signature" expands to "Best regards, David"). Triggers are natural language phrases because that's what the speech engine outputs. Matched longest-first to prevent collisions.
- Whitespace cleanup — Collapses spaces, fixes punctuation spacing, capitalizes the first letter
Every dictation stores both the raw and clean transcript so you can always see what changed.
AI features are entirely opt-in and separate from speech recognition — transcription is always local. The LLM only sees transcript text, never audio.
What it does:
- Summarize — After a transcription finishes, click Summarize and pick a prompt ("Summary", "Action Items & Decisions", "Chapter Breakdown", etc.) or write your own. The LLM processes the transcript and streams back a summary. You can generate multiple summaries per transcript, each in its own tab. Prompts marked as auto-run generate summaries automatically for new transcriptions.
- Chat — Ask questions about a transcript in a multi-turn chat interface. The LLM answers based on the transcript content.
- AI formatter — Optionally run your dictation and file transcripts through your AI provider to clean up grammar, punctuation, and paragraphing. Toggle on/off, customize the prompt, or reset to default.
- Transforms — Select text in any app and press a bound Transform hotkey, such as
Option-1for Polish, to rewrite the selection through your configured LLM provider.
Supported providers:
| Type | Options |
|---|---|
| Cloud | Anthropic (Claude), OpenAI, Google Gemini, OpenRouter |
| Local | Ollama, LM Studio |
| Custom | OpenAI-Compatible (any API-shaped endpoint — vLLM, LocalAI, LiteLLM, llama.cpp server, third-party hosts) |
| CLI subprocess | Claude Code, Codex, or another configured command |
Setup: In Settings → AI Provider, pick a provider, enter an API key (cloud) or confirm the local server/CLI command is available, select a model, and hit Test Connection. Cloud providers store keys in the macOS Keychain. Ollama and LM Studio can keep LLM inference on-device. CLI subprocess providers run the configured command locally, but that command may contact its own cloud service.
All speech recognition runs locally. Parakeet uses the Neural Engine; the optional WhisperKit engine also runs on-device. Your audio never leaves your Mac.
- No cloud STT. The model runs on-device. No audio is transmitted.
- No accounts. No login, no email, no registration.
- Opt-out telemetry. Non-identifying usage analytics and crash reporting go to a self-hosted endpoint only when telemetry is enabled. No persistent IDs, no IP storage, and no transcript/audio content is transmitted. Source code is right here — verify it yourself.
- Temp files cleaned up. Audio deleted after transcription unless you save it.
What does use the network: AI summaries and chat connect to configured LLM providers, or to whatever service a configured CLI tool chooses to use, when you choose them. Sparkle checks for app updates. YouTube transcription downloads video via yt-dlp. Telemetry and crash reports go to our self-hosted server unless you opt out. Core dictation and transcription stay fully offline.
Note: Builds from source also send telemetry by default. Opt out in Settings or set MACPARAKEET_TELEMETRY_URL to override.
- Report bugs — Open an issue with steps to reproduce and relevant logs or screenshots.
- Discuss new work first — For features or behavior changes, open an issue before starting a PR so we can agree on scope and product fit.
- Submit scoped PRs — Once the issue direction is clear, fork, make the scoped changes, run
swift test, and link the issue in the PR. - Read the specs — Architecture decisions and feature specs live in
spec/
MacParakeet is free and open source. If it's useful to you, consider sponsoring.
GPL-3.0. Free software. Full license.