Mode Settings

Triggers

The top of the Mode editor controls when the Mode activates. For matching behavior, see Mode Triggers.

Setting	What it does
Triggers	Adds apps, websites, suggested trigger groups, or spoken word triggers.
Keyboard Shortcut	Starts recording directly with this Mode.

Transcription

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

Setting	What it does
Model	Chooses the transcription model for this Mode.
Real-time	Processes audio while recording when supported. Some models require it. Settings → Interface → Live Text Display controls whether partial text is visible.
Language	Chooses a supported language. Some models use Autodetected automatically.
Paragraph breaks	Applies intelligent paragraph formatting to longer transcripts.

AI Enhancement

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

Setting	What it does
AI Provider	Chooses a connected enhancement provider.
AI Model	Chooses the provider model. Supported providers offer Custom… for an exact model ID. Local CLI uses the model specified by its command; Refine uses its fixed 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. See Context Awareness.

Turning AI Enhancement on selects available defaults when the Mode does not already have them. A working connection or downloaded enhancement model is still required.

VoiceInk Refine has a fixed cleanup task and does not expose custom Prompt or Context controls. It cannot use Respond output. Local CLI generates enhanced text through your configured command.

Advanced

Setting	What it does
Output	Chooses where the final text goes after transcription and optional AI enhancement.
Set as default	Uses this Mode when no app or website trigger matches. Respond Modes cannot be default.
Custom Command	Runs a local shell command with the final text. See Custom Commands.

Output Modes

Output controls delivery. The Mode still uses its transcription, formatting, prompt, and context settings first. Then VoiceInk delivers the final text using the selected output mode.

Mode	Best for	What happens
Paste	Normal dictation, chat, email, notes, forms	VoiceInk pastes the final text into the active app. The global Auto Send setting applies when you stop recording with Return.
Respond	Assistant-style questions and follow-ups	VoiceInk keeps the AI response inside the recorder instead of pasting it. See Assistant Mode.
Custom Command	Local workflows and automations	VoiceInk runs your shell command and gives it the final text. See Custom Commands.

Respond is available only when AI Enhancement has a connected provider and selected prompt. VoiceInk Refine does not support it. A Respond Mode cannot be the default Mode. See Assistant Mode for the full workflow.

Custom Command runs locally with your user permissions. VoiceInk sends the final text on stdin and also exposes it as VOICEINK_TRANSCRIPT. This is useful for workflows like copying a modified transcript, appending to a journal, opening a search, or handing text to another script. See Custom Commands for examples and technical details.

Auto Send and Imported Files

Auto Send lives in Settings → Pasting. When enabled, pressing Return while recording finishes the recording, pastes its result, and presses the selected send key. Stopping with your normal recording shortcut only pastes. See Shortcuts.

Imported files use the selected Mode's processing choices but do not capture live context, paste, open Respond conversations, execute Custom Commands, or Auto Send.