Dictation

Whisper Dictation records from the Mac microphone and transcribes speech locally. It inserts text into the composer without sending the message.

Set up

1. Open Plugins.
2. Install and enable Whisper Dictation.
3. Download the multilingual model.
4. Wait for the model to show as verified on-device.
5. Start dictation from the composer and approve microphone access when macOS asks.

The plugin runtime and model weights are separate. Installing the plugin exposes the action; downloading the model enables local inference.

Use dictation

1. Start recording.
2. Speak normally in a supported language.
3. Stop recording.
4. Review and edit the inserted text.
5. Send only when it says what you intend.

Audio and model files remain local to the app. Silence, very short recordings, or missing microphone permission can prevent transcription.

See macOS permissions for recovery steps.