Support
We're here to help
Need Help?
Have a question, found a bug, or want to suggest a feature?
We'd love to hear from you.
FAQ
Q. Does NoteVox require an internet connection?
No. NoteVox uses WhisperKit, an on-device AI engine, to transcribe speech. All processing happens locally on your device — even in airplane mode. An internet connection is only needed for the one-time AI model download (~600 MB) on first launch.
Q. Which languages are supported?
NoteVox supports 100+ languages through the Whisper AI model, including English, Korean, Japanese, Chinese, Spanish, French, German, and many more.
Q. How does iCloud sync work?
With iCloud enabled, your recording metadata (titles, timestamps, tags, and transcripts) automatically syncs across your Apple devices. Raw audio files stay on each device. All synced data is encrypted and stored in your personal iCloud account.
Q. Is my audio data private?
Yes. All audio processing happens on your device. We never collect, transmit, or store your audio recordings or transcriptions on any server. See our Privacy Policy for details.
Q. Can I import audio files from other apps?
Yes. NoteVox supports Share Extension — you can send audio files from Files, Voice Memos, or any other app directly to NoteVox for transcription.
Q. What AI model does NoteVox use?
NoteVox uses WhisperKit with OpenAI's Whisper large-v3 model, optimized to run entirely on Apple Silicon. No cloud processing required.
Q. The first transcription is taking a long time — is that normal?
Yes. On first use, NoteVox downloads the Whisper AI model (approximately 600 MB). This is a one-time download; subsequent transcriptions are instant.
System Requirements
- iOS 26.0 or later
- iPhone and iPad compatible
- Approximately 700 MB of storage (includes AI model)
- Apple Silicon recommended for best performance