Long recordings, local workflow

Transcribe audio on your Mac without a per-minute meter.

Drop a supported audio file into AFK, let the on-device speech engine work through it in chunks, and save the result as text, subtitles, or timestamped JSON.

Get AFK — $15 once Read the file guide

The useful part

Built for recordings that do not fit in a text box.

Interviews, lectures, voice memos, and other long audio can be queued from the Transcribe tab. AFK streams source audio in 120-second chunks, transcribes each chunk, and shifts word timings back onto the full recording timeline.

Queue the work

Choose multiple audio files or drag them into the app. Jobs run one at a time and can be removed while queued, running, or complete.

Keep the timings

When the model returns word timings, AFK can show timestamped segments and use them for SRT or JSON export.

Save your copy

Save TXT, SRT, or JSON. Unsaved non-empty results stay in the local cache for one hour; saving creates a lightweight History reference.

AFK Transcribe screen showing the audio drop zone, supported audio extensions, and local processing note.
The Transcribe screen keeps supported audio formats and local processing in view. Click the image to open a full-size view.

Supported audio inputs

Use the formats the current app handles.

The drop target explicitly recognizes these extensions, and the file picker accepts audio types recognized by macOS.

  • .m4aCommon voice-memo and compressed audio files.
  • .wavUncompressed PCM audio.
  • .mp3Compressed audio.
  • .aiff / .aifAIFF audio files.
  • .cafCore Audio Format files.
  • .flacLossless audio files.

The app's file picker is for audio. The separate CLI also accepts an .mp4 file when it contains an audio track.

Formats and languages

Useful output, with a model you can understand.

The default Parakeet v3 model is multilingual across 25 European languages. AFK can also use an English-only Parakeet v2 model from the app's settings.

See the language list →

Export from the result card

  • TXT for a readable plain-text transcript.
  • SRT for subtitle-sized timestamped segments.
  • JSON for text, duration, and word timings.

Local by design

Audio processing stays on the Mac after model setup.

The first run needs the network to download and optimize the model. After that, file reading and speech recognition run locally. License activation and Sparkle update checks are separate network operations.

Read the exact privacy boundary →

Ready for the long one?

Keep the recording. Keep the transcript.

Install AFK, set up the model once, and make the next long audio file a local job.

Buy AFK — $15 once Get started