VoiceInk Docs
Common Issues

Model or Language Changing Automatically

Why Modes can change your model, language, prompt, or output behavior.

Why Settings Change

VoiceInk records through Modes. A Mode can save its own transcription model, realtime setting, language, formatting behavior, AI provider, AI model, prompt, context sources, output behavior and shortcut. Auto Send is a global Pasting setting, not a per-Mode choice.

When a Mode becomes active, those saved settings are used for the recording.

Check the Active Mode

Open Modes and look at your enabled Modes.

Settings may change because:

  • A Mode matches the active app.
  • A Mode matches the active website.
  • A trigger group matches the current app.
  • A Mode is marked as the default.
  • You used a Mode shortcut.
  • You spoke a configured word trigger at the beginning or end of your dictation.

See Mode Triggers for how matching works.

The Default Mode Applies Everywhere

A default Mode is used when no more specific app, website, or group trigger matches. If the default Mode uses a different model or language, VoiceInk can feel like it is changing settings on its own.

To change this:

  1. Open Modes.
  2. Select the Mode marked as default.
  3. Make the intended Mode the default. Respond Modes cannot be the default.

Disable or Reorder Modes

If a Mode is matching too often, you can disable it without deleting it. You can also reorder Modes so your most important workflows are easier to inspect and manage.

If two Modes feel similar, open each one and compare the transcription, AI enhancement, context, and output sections. See Mode Settings.

Language Changes

Language is configured per Mode. Open the active Mode and check its transcription language setting.

Some models and providers handle language selection differently. An unavailable language can fall back to automatic detection or a supported default. If a provider ignores a language choice or performs poorly in a language, try another transcription model from AI Models.

Word Triggers and Interface Language

A spoken word trigger switches post-transcription processing. It does not rerun the recording through the triggered Mode's transcription model or language.

Settings → Interface → Language changes the app's interface after restarting. It does not choose the language you dictate in.