Support

Voice Ledger records long conversations (lectures, meetings, interviews, or any recording with speech in it) and turns them into transcripts you can edit, search and export. It also imports audio and video files you already have, and transcript files (SRT, VTT, plain text). Processing runs on your device after the required speech and optional AI model assets are installed.

There is no limit in the app. A three-hour recording is a normal thing to do: it transcribes in a few minutes and takes about 14 MB of storage per hour of audio. The practical limit is the free space on your device, and the app shows you how much recording time you have left before you start.

Yes, after setup. Recording, editing, search and export are local. Transcription works offline after Apple has supplied the required recognition-language asset, and optional AI features work offline after you start and complete their model download from Hugging Face. StoreKit also uses a connection for plans, purchase and restore.

No. Your recordings, transcripts and notes are stored locally on your device and are not transmitted to Studio AM or included in an optional model-download request. There is no Voice Ledger account, no sign-in and no Studio AM processing server.

There is no free tier. Recording, transcription and importing require a subscription. In the US, the monthly plan is $7.99 and may include a 3-day trial for eligible new subscribers. The yearly plan is $39.99 with no introductory offer. Apple shows eligibility and local terms before purchase.

The download starts only when you choose it and goes directly to Hugging Face. The request contains no recording, audio, transcript, question, summary or saved app content. Hugging Face may record and retain approximate location derived from your IP address, device diagnostics and the model-download interaction for app functionality, analytics and other purposes under its privacy policy. Studio AM receives none of that provider data, analytics or tracking.

Nothing is taken away. Everything you already recorded or imported stays readable, playable, searchable and exportable forever, with or without an active subscription. You can also rename and organise your existing logs. The subscription covers making new recordings, running transcription, and importing.

Yes. The transcript is a draft you can edit. Corrections keep their link to the audio, so tapping an edited line still plays the moment it came from. You can also name speakers by hand, and a name you set is applied everywhere it appears.

No. Apple’s on-device speech engine does not offer automatic speaker separation, so the app does not claim to do it. You can label speakers yourself, which is accurate because you decide it.

Yes. Import an .srt, .vtt or .txt file, or paste text directly. Timings are kept when the file has them. You can also import audio and video files you already have and transcribe them. The app never downloads or extracts content from YouTube or any other service; it works only with files you already have or text you paste.

Transcription is intensive, and iPhones slow down when they get warm. If your device is hot, the app tells you that a transcript will take longer, and if it gets too hot it waits rather than stalling silently. Recording itself is never paused or stopped for heat.

Open a log and export the audio file, the transcript as plain text or as SRT/VTT with timings, or export everything as lossless JSON. Export is never behind the subscription. Settings also has a delete-everything option that removes local data without touching your Apple subscription.