Docs/Settings/AI

AI

This tab sets what every new conversation starts with — which AI model it uses and how hard that model thinks — plus your API key and voice dictation. If you want a particular thinking tool to use a different model, that's set on the Skills tab; here you're just setting the defaults everything else falls back to.

Default model and effort

Two dropdowns pick the starting point for a fresh conversation. They're only defaults: each conversation has its own model and effort pickers that override them for that conversation, and changing them here never disturbs a conversation you already have open.

Default model
Choose which model new conversations use. Faster models answer quickly and cost less; more capable ones handle harder, more nuanced work.
Default reasoning effort
How long the model spends thinking before it answers, from Low up to Max — or leave it at the model's own default. More effort can mean better answers on tricky questions at the cost of a little speed. Not every model offers every level; you'll only ever be offered the levels the chosen model actually supports.

API key

Minerva's AI features need an API key, which you paste into this field. A line above the field tells you whether a key is already saved. For your privacy the saved key is never shown back to you, and it can't be copied out of the field.

Entering a key
Paste your key into the field and click Done to save it. If a key is already saved, typing a new one replaces it.
Clearing a key
Once a key is saved, a Clear saved key link lets you remove it. Nothing is deleted until you click Done, and a Cancel clear link lets you change your mind first.

Voice dictation

Turn on Enable voice dictation to speak instead of type, and pick a voice model from the dropdown beside it. Dictation runs entirely on your own machine — your audio never leaves it. The first time you use it, the voice model downloads once and is then ready to use offline.

The AI settings panel: a default model dropdown and a reasoning effort dropdown, then the API key section showing whether a key is saved, and at the bottom the voice dictation toggle with its model choice.
Screenshot — the AI settings tab