Get started
Models we use
Exactly which speech and language models run on your Mac and in Infina Cloud.
Infina works on your Mac and offline by default. 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 exactly what powers each mode, named in full.
On your Mac, included with your license
These models download once and then run fully on-device and offline, included with your lifetime license.
- Parakeet turns your speech into text. It is NVIDIA's Parakeet model, running on the Apple Neural Engine.
- Qwen3 0.6B is the small on-device language model behind the voice assistant and voice actions.
- 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 large-v3 handles speech recognition. It is a much larger and more accurate speech model than anything that fits on a laptop.
- Qwen3 32B cleans up and formats your text and powers the assistant. At 32 billion parameters it is 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.