AFK guides.

Install the app, get the model ready, choose how dictation behaves, transcribe long audio, and connect the same engine to a shell.

Choose the next useful step.

These guides describe the current AFK app and CLI. When a boundary matters, the guide says so.

Start

Install AFK and finish setup

Requirements, signed install, first-run model setup, license activation, permissions, and your first dictation.

Dictate into any app

Hold-to-talk, hands-free sequences, clipboard fallback, cleanup, language, and the custom dictionary.

Do the work

Transcribe a recording

Supported inputs, chunking for long recordings, queue controls, result expiry, history references, and exports.

Find past dictations and files

Search dictations, expand long notes, use visible copy/delete actions, and reopen saved transcription files.

Automate

Use AFK from the command line

Transcribe audio or MP4, understand output streams, flags, exit behavior, and shell recipes.

Let an agent do the transcribing

Install the bundled Agent Skill and give a coding agent a clear, local command workflow.

When stuck

Fix a problem

Work through model setup, permissions, shortcut, audio-input, missing-result, update, and CLI problems.

Privacy and network boundaries

See the model download, Polar activation, Sparkle update checks, local history, and one-hour cache behavior.