Get started
Models we use
Exactly which speech and language models run on your Mac and in Infina Cloud.
Once Infina is running, your dictation works on your Mac without an internet connection. Everything you say is turned into text and tidied up by models that run on the device, so your voice and your words never leave your Mac. Infina Cloud is an optional add-on that runs much larger models on our servers when you want fully polished text. Here is what powers each mode.
On your Mac, included with your license
These models download once and then run fully on-device, with no internet connection needed once Infina is running, included with your lifetime license.
- Parakeet TDT 0.6B v2 turns your speech into text. It is NVIDIA's Parakeet model at 0.6 billion parameters, running on the Apple Neural Engine.
- Qwen3 0.6B is the small on-device language model behind the voice assistant and voice commands.
- Vosk is a small on-device streaming speech model we use to catch the trigger words for hands-free mode. It runs quietly in the background and only ever picks up your trigger words like type, send and Jupiter, so nothing is sent anywhere until you speak one.
Infina Cloud, optional add-on
Some models are simply too big to run well on a Mac. With Infina Cloud they run on our servers instead, so your dictation comes back fully polished in every app, with grammar, punctuation and formatting handled for you.
- Whisper — its biggest, most accurate versions handle speech recognition. Whisper's best models are simply too large to run on a laptop, which is exactly why they live in the cloud.
- Llama and Qwen — large versions of these models clean up and format your text and power the assistant. They are far beyond what a Mac can run on its own.
Cloud is entirely optional. On-device dictation and the assistant come with your lifetime license, run locally and stay private, and you can switch between on-device and cloud whenever you want.