NabuVoice 1.0.37 · macOS
Dictation that never
leaves your Mac.
Hold fn, speak, release. The words land at your cursor in whatever app you're in — transcribed by a speech model running on your own machine, then tidied by a local language model.
Standup — Thursday
Today I'm finishing the uuid migration, then pairing on the theme contrast audit
Speak anywhere.
Nothing goes to a server.
Push-to-talk, anywhere
Hold your hotkey — fn by default — speak, and release. It works without switching windows or clicking into anything.
Works in every app
Text is inserted at your cursor through the accessibility layer, with a clipboard paste as the fallback.
Thirteen local speech models
Parakeet, Canary, SenseVoice, Moonshine and Whisper. Download one once and transcription stays on-device.
Cleanup by a local LLM
Grammar and formatting are tidied by a small model running through llama.cpp on Metal, on the same machine.
Vocabulary and snippets
Teach it your names, jargon and acronyms, and expand a spoken shortcut into a full block of text.
Notes and per-app rules
Capture a thought as a note in the app, and set rules that change behaviour per application.
Privacy
Private by design. Local by default.
A dictation app hears everything you say, including the half-sentences you throw away. That is exactly why this one keeps the audio on the machine that heard it. Your account only knows that you own a license — there is no server in the audio path to trust, and nothing to switch off before you say something private.
- Your voice
- Models on your device
- Text in your app
The whole pipeline runs with the network off
Of your audio stays on-device when you transcribe with a local model.
Local speech models, from Parakeet TDT v3 to seven Whisper variants.
Local correction models running through llama.cpp on Metal.
The models
Eighteen models. All of them yours.
Nothing here is a hosted endpoint with a friendly name. These are weights that land on your disk, get checked, and then run without asking anyone's permission.
Speech models
The transcriber. Pick one in the app, download it once, and it runs on your hardware from then on.
- Parakeet TDT v3Default
- Parakeet TDT v2
- SenseVoice
- Moonshine Base
- Canary 180M Flash
- Canary 1B v2
- Seven Whisper variants
Correction models
The proofreader. A small language model tidies grammar and formatting through llama.cpp on Metal, listed here smallest first.
- Qwen2.5 1.5BDefault
- SmolLM2 1.7B
- Qwen3 4B
- Qwen3 8B
- Qwen3 14B
Every model artifact carries a sha256 checksum and is verified after download, so a corrupted or substituted file never gets loaded.
Open source
Built in the open.
MIT, not source-available
The permissive one. Use it, fork it, ship something on top of it. NabuCode is proprietary; this one is not.
Paid once, not metered
NabuVoice is a one-time lifetime license on your NabuSuite account — no subscription and no per-minute metering, because your machine does the transcribing.
Auditable rather than promised
The privacy story on this page is a claim about code. When the repository is public it becomes something you can check instead of something you have to believe.
Source
The repository is not public yet, so there is nothing here to link to. It goes up with the first release, under the licence above.
How it works
01
Buy and download
Buy a lifetime license, then download NabuVoice for your Mac (Apple silicon, macOS 12 or later).
02
Sign in
Sign in to the app with the same email you bought with. The license is already on that account.
03
Hold fn and talk
Pick a speech model on first run. From then on, hold the hotkey anywhere and speak.
Lifetime license
Pay once. Keep NabuVoice for good.
No subscription and no account required. The first 1,000 licenses sell at the launch price — after that, NabuVoice is $39.99.
- All thirteen speech models
- Local LLM cleanup
- Up to 3 Macs
- Updates included
- No subscription, no metering
- Audio never leaves your Mac
NabuVoice
Launch price