Mode Settings

Transcription

For transcription, you can manage all the available local and cloud models from the AI Models catalog.

Mode transcription settings:

Setting	What it does
Model	Chooses the transcription model for this Mode.
Real-time	Shows partial transcript while recording when the model supports streaming.
Language	Chooses a supported language or Autodetected.
Paragraph breaks	Splits longer text into paragraphs.
Punctuation	Keeps punctuation, removes all punctuation, or removes only a trailing period.
Lowercase output	Converts transcription output to lowercase.

When AI Enhancement is enabled, the Mode can clean up text, rewrite selected text, draft emails, or answer questions.

Enhancement settings:

Setting	What it does
AI Provider	Chooses a connected enhancement provider.
AI Model	Chooses the provider model.
Prompt	Chooses a prompt. You can edit the selected prompt or add a new one from the Mode editor.
Context Awareness	Lets the prompt use selected text, clipboard text, and/or visible screen text.

Setting	What it does
Output	Chooses Paste or Respond. Respond is available only when enhancement is configured.
Set as default	Uses this Mode when no app or website trigger matches. Only applies to Paste output.
Auto Send	Presses Return, Shift+Return, or Command+Return after pasted text.
Keyboard Shortcut	Assigns a shortcut that activates this Mode and starts recording.

Paste sends the final text into the active app. It can also auto-send after a short delay.

Respond keeps the AI response in the recorder. It is intended for the Assistant Mode and other question-answer workflows.