Your voice never leaves your Mac
Every word you speak is processed entirely on your device. No cloud servers, no audio uploads, no third-party access. Hearsy is built from the ground up for complete voice privacy.
Three pillars of privacy
Hearsy's privacy isn't a setting you toggle on — it's the architecture. Every component is designed to keep your data on your machine.
No cloud processing
Both speech-to-text engines — Parakeet and Whisper — run entirely on your Mac using local neural network models optimized for Apple Silicon. There is no server in the loop.
No audio uploads
Your microphone input is processed in real-time memory and discarded immediately. No audio files are written to disk, cached, or buffered for later transmission.
No data collection
Hearsy doesn't have analytics, telemetry, or usage tracking. We don't know what you dictate, how often you use the app, or even that you're running it.
Why local processing matters
Voice dictation captures your most unfiltered thoughts — meeting notes, medical records, legal documents, personal journals, passwords spoken aloud. This data is deeply personal and often professionally sensitive.
Cloud-based dictation services require sending raw audio to remote servers where it's processed, potentially logged, and stored in databases you don't control. Even with encryption in transit, your audio exists on someone else's infrastructure.
Local processing eliminates the entire attack surface. There's no network request to intercept, no server to breach, no database to leak. Your voice data exists only in your Mac's memory for the brief moment it takes to transcribe — then it's gone.
What we don't collect
Most companies list what they collect. We list what we don't — because the list is everything.
Audio recordings
Processed in memory, never saved
Transcription text
Pasted to your app, then discarded
Usage analytics
No tracking, no telemetry, no metrics
Device identifiers
No fingerprinting or device tracking
Crash reports
No automatic error reporting
IP addresses
No server means no network logs
Local vs. cloud dictation
See how Hearsy's local-first approach compares to cloud-based dictation services.
Hearsy (Local)
- ✓ Audio processed on-device only
- ✓ Works fully offline
- ✓ No data leaves your Mac
- ✓ No server to breach
- ✓ HIPAA/GDPR friendly by design
- ✓ Zero telemetry or tracking
Cloud Dictation
- ✗ Audio sent to remote servers
- ✗ Requires internet connection
- ✗ Data processed on third-party infra
- ✗ Potential for data breaches
- ✗ Requires compliance agreements
- ✗ Usage analytics collected
Privacy FAQ
Dictation that respects your privacy
Download Hearsy and keep your voice where it belongs — on your Mac.
macOS 14+ · Apple Silicon · 100% local processing