Privacy-First Processing: Your voice recordings are transcribed locally on your device using OpenAI’s Whisper model. Your audio never leaves your device.
How Transcription Works
- Record your voice by tapping the microphone and speaking naturally
- Stop recording when you’ve captured your complete thought
- Transcription begins immediately using the Whisper AI model on your device
- Review your transcript once processing completes (usually within seconds)
Transcription Features
High-Accuracy Processing
- Industry-leading accuracy with Whisper AI model
- Automatic punctuation and formatting
- Technical terminology recognition
- Natural speech patterns understanding
Language Support
- Multiple languages supported
- Automatic language detection
- Regional accent recognition
- Proper noun handling
On-Device Benefits
- Complete privacy - audio never leaves your device
- Fast processing - typically completes in seconds
- Offline capability - works without internet connection
- Secure storage - encrypted locally on your device
Maximizing Transcription Accuracy
Best Practices
- Speak clearly and at moderate pace
- Use quiet environments when possible
- Position microphone toward your mouth
- Speak naturally - do not over-enunciate
What to Expect
- Processing completes in seconds
- High accuracy even with technical terms
- Automatic punctuation and capitalization
- Editable transcript before AI processing
Working with Your Transcript
After transcription completes, you can:- Review and edit the transcript text directly
- Regenerate the note if you make transcript changes
- Access raw transcript anytime via the transcript toggle
- Create AI-organized notes from the transcript text
The transcript captures exactly what you said - you can always edit it before generating your organized note to fix any misheard words or add clarifications.