HoldSpeak
Website: holdspeak.app · Download · Free Superwhisper alternative — comparison
Local push-to-talk dictation for macOS. HoldSpeak is a menu bar app (no Dock icon, no windows in the way) — it lives in the status bar and stays out of your workflow until you hold the hotkey. Speak, release — recognized text is inserted into the focused input. Local by default: NVIDIA Parakeet Ultra (macOS 14+) or OpenAI Whisper Turbo (via WhisperKit) runs on this Mac. Optionally, you can switch to Google Gemini or OpenAI with your own API key.
A free, local alternative to paid Whisper wrappers. Built for one reason: talking to AI is faster than typing to it. Average typing speed hovers around 40–60 wpm; comfortable speech is 130–160 wpm — two to three times faster. As more of the dev loop moves into prompts to AI agents, raw typing throughput becomes a real ceiling on how quickly you can iterate. HoldSpeak lifts it: hold the hotkey, speak a full thought, release, it lands in the input.
Features
- Local transcription through WhisperKit (CoreML, GPU)
- Optional cloud engines — Google Gemini or OpenAI with your own API key, for higher accuracy on mixed-language speech and jargon
- Code-switching RU/EN/UK and more — in auto mode the language is chosen only from the ones you have in System Settings → Language & Region
- Insertion without clipboard — via
CGEventKeyboardSetUnicodeString; password fields are skipped
- Menu bar popover with recent transcriptions (click to copy) and metrics: dictations today / yesterday, 7-day avg WPM, each with its change vs. a week ago
- HUD overlay while you hold the key: dark pill with a live mic level; if a dictation fails (no model, bad API key, quota), the reason shows in the same pill
- Light text cleanup — trims long "eeeeee / mmmmm / ummm", collapses 3+ consecutive repeats, capitalizes the first letter and adds a period
- Optional filler-word removal — off by default; drops "ну / короче / как бы / um / you know" from an editable list (Whisper, OpenAI) or by context (Gemini)
- Liquid Glass on macOS 26 and later — the HUD, popover, Preferences and onboarding use the system glass; macOS 13–15 keep the classic look
- Terminology dictionary — canonical IT terms (pull request, Kubernetes, Claude Code, …) replace misrecognized Russian transliterations in transcripts; ships with ~110 defaults and is fully editable
Install
Requires a Mac with Apple Silicon (M1 or later) and macOS 13 or later.
Grab the latest DMG from the Releases page, open it, and drag HoldSpeak.app into Applications.
Because the app is self-signed, macOS will block the first launch. Open System Settings → Privacy & Security, scroll to the message "HoldSpeak was blocked…" and click Open Anyway. Confirm with Touch ID / password. After that it launches normally from Launchpad / Applications. The app runs as a menu bar extra — look for the radio icon in the right side of your menu bar; it won't appear in the Dock or Cmd-Tab.
On first launch, choose how speech is recognized — NVIDIA Parakeet Ultra (on this Mac, fastest, 25 European languages, ~610 MB download; macOS 14+ on Apple Silicon), OpenAI Whisper Turbo (on this Mac, 99 languages, slower, ~1.5 GB), Gemini (Google cloud) or OpenAI (cloud); the cloud engines ask for your API key — then grant three permissions:
- Microphone — for audio capture
- Accessibility — for the global hotkey and text insertion
- Input Monitoring — to use Right Option / Right Cmd (or the hotkey you choose) as push-to-talk
The onboarding window has Open… and Re-check buttons.
Updating
The app checks GitHub for new versions in the background and shows an Update available banner in the menu bar popover. You can also trigger a check manually via Preferences → General → Check for updates.
- Click Download in the banner — it opens the latest release on GitHub.
- Download the
.dmg, open it, and drag HoldSpeak.app into Applications. macOS will ask to replace the old copy — confirm.
- Quit the running app from the menu bar (Quit), then launch the new one from
Applications.
Your preferences, history, and downloaded models live in ~/Library/Application Support/HoldSpeak/ and are preserved across updates.
Model
Preferences → Audio → Model lists the models in two groups, best first in each:
- On this Mac — free, works offline: NVIDIA Parakeet Ultra (fastest, 25 European languages, 610 MB; the default on macOS 14+, hidden on macOS 13) and OpenAI Whisper Turbo (large-v3 distilled, 99 languages, slower, 1.5 GB — the default on macOS 13).
- Cloud — your API key, pay per use: OpenAI GPT Transcribe, OpenAI GPT-4o mini, Gemini 3.5 Transcribe, Gemini 3.5 Flash-Lite — see below. Each item shows its price per hour of speech.
If you already have MacWhisper / another WhisperKit client installed, their models will be picked up automatically. Otherwise the first model is downloaded to ~/Library/Application Support/HoldSpeak/Models/.
To free disk space, Preferences → Audio → Downloaded models → Delete… removes every model HoldSpeak downloaded. Models that belong to MacWhisper or other apps are left alone.
Gemini (optional, cloud)
Pick a Gemini model in Preferences → Audio → Model (or choose Gemini during onboarding) and paste an API key:
This is the beginning of the README. Read the rest at the original. Read the full README ↗
