Support
LocalScribe — Private Voice Transcription
Getting Started
How do I create my first transcript?
Open the app and tap the record button on the dashboard. Live captions appear in real time as you speak. When you stop recording, LocalScribe runs a full Whisper pass on-device for a higher-accuracy timestamped transcript. You can also import audio or video from the Files app or Photos library to transcribe existing recordings.
What's the difference between live captions and Whisper transcription?
Live captions use Apple's on-device speech engine to show words as you speak — instant, but lower accuracy on technical terms or accents. Whisper transcription runs after the recording stops, producing a more accurate timestamped transcript that handles accents, jargon, and proper names. Both run entirely on your iPhone.
Which Whisper model should I use?
Base (free) is fast and works for everyday English speech. Small (free) is more accurate and handles 100+ languages well. Large V3 Turbo (Premium) is best-in-class accuracy for accents, technical content, and noisy environments — recommended for important meetings and interviews. You can switch models in Settings » Manage Models.
Recording & Importing
Can I import audio or video files?
Yes. Tap Import to pick from Files (m4a, mp3, wav, caf, and more) or video clips from Photos (MP4, MOV). LocalScribe extracts the audio and transcribes it locally. The original video is left untouched.
Can I keep recording when I switch apps?
Yes. Live recording continues in the background when you switch to another app or lock your screen. A persistent indicator lets you return to LocalScribe to stop the recording.
Does it work in airplane mode?
Yes. Once you've downloaded a Whisper model, live captions and Whisper transcription work fully offline. You only need the internet for the first-time model download and for managing your subscription.
How long can a recording be?
Free users can transcribe up to 30 minutes per month with files up to 10 minutes each. Premium subscribers have unlimited transcription minutes and unlimited file length. Long files transcribe in the background; you'll get a notification when they're ready.
Transcripts & Export
Can I edit a transcript?
Yes. Tap any line in the transcript detail view to edit inline — changes autosave as you type. Original audio time-alignment is preserved so tap-to-jump still works after edits.
How does tap-to-jump work?
In the transcript detail view, tap any sentence to jump audio playback to that exact moment. The currently-playing line highlights as audio plays. Great for verifying a quote or finding a specific point in a long lecture.
What export formats are supported?
Free: Plain text (TXT). Premium: SRT and VTT subtitles for video editors, PDF with timestamps, Markdown for note-taking apps, and DOCX for Word. Share via AirDrop, Mail, Messages, or any app via the iOS share sheet.
Can I search across all my transcripts?
Yes. The Library tab lets you search every word across your full transcript history. Matching transcripts and the specific lines are highlighted.
Free vs Premium
What's free vs Premium?
Free: 30 transcription minutes per month, Whisper Base and Small models, live captions in 100+ languages, TXT export, supported by banner and interstitial ads. Premium: Unlimited transcription minutes, Whisper Large V3 Turbo, all export formats (SRT, VTT, PDF, Markdown, DOCX), AI Summary with Apple Intelligence, background transcription for long files, unlimited file length, and zero ads.
Is there a free trial?
Yes — the Premium Annual plan ($39.99/year) includes a 7-day free trial. You'll only be charged at the end of the trial. Cancel anytime in your Apple ID subscription settings before the trial ends.
How do I restore my purchase?
Open Settings inside the App and tap "Restore Purchases". This re-applies your active subscription if you've previously purchased one on this Apple ID.
How do I cancel my subscription?
Open the iOS Settings app, tap your name at the top, then tap Subscriptions. Find LocalScribe and tap Cancel Subscription. Cancellation takes effect at the end of the current billing period.
Privacy
Where do my recordings and transcripts go?
They stay on your iPhone. The App does not upload audio or transcripts to any server. Live captions use Apple's on-device speech engine; Whisper runs locally with a model bundled in the app. You can confirm by toggling Airplane Mode — transcription still works. See the Privacy Policy for full details.
What permissions does the app need?
Microphone (only when you tap Record), Speech Recognition (for on-device live captions), Files / Photos (only the files you pick), and Notifications (optional, for background-processing completion alerts).
Does iCloud sync upload my transcripts?
iCloud sync is optional and uses your personal iCloud account — we never see your data. If enabled, recordings and transcripts sync between your own Apple devices under Apple's privacy terms. Disable in Settings if you want everything to stay only on the current device.
Troubleshooting
The transcript has errors. How can I improve accuracy?
Switch to a larger Whisper model in Settings » Manage Models. Large V3 Turbo (Premium) handles accents, technical terms, and proper names significantly better than Base or Small. Make sure to enable the correct language hint if auto-detect picks wrong — speech recognition is noticeably more accurate when the language is set explicitly.
Transcription is slow on my device.
Whisper transcription speed depends on your iPhone model and the model size. Large V3 Turbo runs in near real-time on iPhone 15 Pro and newer; on older devices, expect 2-3x audio length for the full transcription. Live captions are fast on all supported devices because they use Apple's on-device speech engine.
A model failed to download.
Whisper model weights are downloaded on first use. If a download fails, check your internet connection and free storage (Large V3 Turbo needs ~1.5 GB). Settings » Manage Models lets you retry. Once downloaded, models work offline forever.
Contact Us
Email Support
For questions, bug reports, or feature requests:
We typically respond within 48 hours. If you're reporting a bug, mentioning the Whisper model you were using and your iPhone model helps us reproduce.