Support

1. Tap "Choose Source" on the main screen
2. Select "Browse Files" to pick from Files app, or "Photo Library" for videos
3. Choose your audio/video file
4. VoxScript will automatically transcribe it (takes 1-2 minutes per minute of audio)
5. View the transcription with timestamps and audio playback

VoxScript supports most common audio and video formats:

Transcription speed depends on:

• File length — Generally 1-2 minutes of processing per minute of audio
• Device model — Newer iPhones (iPhone 13+) are faster
• Model selection — Tiny model is faster, Base model is more accurate but slower
• First use — The AI model downloads on first transcription (40-140 MB)

Processing happens entirely on your device for privacy, which takes longer than cloud services but keeps your data secure.

1. Tap the gear icon in the top-right corner
2. Select your preferred model:
   • Tiny — Fast, smaller download (~40MB), good accuracy
   • Base — Slower, larger download (~140MB), better accuracy
3. The model will download on your next transcription if not already installed

After transcription completes:

• Export as Text — Creates a .txt file with the transcription and timestamps
• Export as SRT — Creates a subtitle file (.srt) for video editing software

Both options use the iOS share sheet — you can save to Files, send via email, or share to other apps.

No internet required after setup. On your first transcription, VoxScript downloads the selected AI model (one-time download). After that, everything works completely offline. Your audio files never leave your device.

Yes, completely. VoxScript:

• Processes everything on your device
• Never uploads audio files to any server
• Doesn't collect any user data
• Doesn't require an account or login
• Has no analytics or tracking

See our Privacy Policy for full details.

VoxScript supports 80+ languages through the Whisper AI model, including:

• English, Spanish, French, German, Italian, Portuguese
• Chinese (Mandarin), Japanese, Korean
• Arabic, Hindi, Russian
• And many more...

Language is detected automatically from the audio.

Transcription accuracy depends on:

• Audio quality — Clear audio with minimal background noise works best
• Speaker clarity — Distinct speech is easier to transcribe
• Accents — Strong accents may reduce accuracy
• Technical terms — Specialized vocabulary may be misinterpreted
• Model choice — Try the Base model for better accuracy

For best results, use clear recordings in quiet environments.

No. VoxScript only transcribes pre-recorded audio and video files. It does not support:

• Live recording and transcription
• Real-time speech-to-text
• Phone call recording

You must first create an audio recording using another app (like Voice Memos), then import it into VoxScript.

1. Export your transcription as SRT format
2. Import the SRT file into your video editing software:
   • Final Cut Pro — File → Import → Captions
   • Premiere Pro — Import SRT as a caption track
   • DaVinci Resolve — Import SRT in the subtitle panel
   • YouTube — Upload SRT when adding subtitles
3. Adjust timing if needed in your editor

Try these solutions:

• Restart the app
• Free up storage space (transcription models need 40-140MB)
• Try a shorter audio file first to test
• Switch to the Tiny model if using Base
• Restart your iPhone
• Ensure iOS is up to date (iOS 17.0 or later required)

• Check your internet connection
• Ensure you have enough free storage (40MB for Tiny, 140MB for Base)
• Try restarting the app and attempting transcription again
• If problem persists, delete and reinstall the app

• Make sure Files app has permission to save files
• Check that the receiving app (email, etc.) is properly installed
• Try exporting again after restarting VoxScript
• Free up storage space on your device