Voice to Text
Private, Simple & Fast
Local AI-powered transcription that never leaves your device
Zero-Network Guarantee
All speech recognition runs locally on your device. No audio ever leaves your computer.
Sub-500ms Latency
From speech to text in under half a second. Press, speak, done.
Stays Out of Your Way
Lives in your menu bar. Press, speak, release, text appears at your cursor.
Metal Acceleration
Optimized for Apple Silicon with GPU acceleration for blazing fast transcription.
Everything you need
Powerful features that respect your privacy
Push-to-Talk Recording
Press ⌥+Space to record. Release to transcribe. Text appears at your cursor instantly.
File Transcription Included
Import audio files of any length to transcribe recordings, meetings, and podcasts. No premium tier or time limits, included with every license.
99 Languages
Whisper supports transcription in over 99 languages with automatic language detection.
LLM Refinement
Improve transcription accuracy with local LLM-based refinement that fixes phonetic errors and domain-specific terminology.
System-Wide Hotkey
Works in any application. Email, code editors, chat apps, documents, transcribe anywhere.
Private by Design
100% offline operation. No cloud, no accounts, no data collection. Your voice stays yours.
Choose Your Plan
Standard
For personal productivity
Core Features
- Unlimited Dictation: System-wide mic input
- Audio File Transcription: Import .mp3, .wav, .m4a
- Single File Processing: Transcribe one recording at a time
- LLM Refinement: Fix phonetic errors & domain terminology
- Privacy First: 100% Offline Processing
Export & Data
- Export as Text (.txt)
- Lifetime Updates included
Pro
For creators, video editors, and power users.
Everything in Standard, plus:
- Creator Suite: Direct Video Import (.mp4, .mov)
- Subtitle Export: Generate .srt & .vtt for YouTube
- Batch Engine: Drag & drop multiple files at once
- Smart Formatting: Speaker Diarization & AI Formatting
Export & Data
- Export as JSON for developers
- HIPAA Compliant Local Storage
Enterprise
For organizations requiring control & scale.
Organization Control
- Centralized Mgmt: Deploy via Jamf / MDM
- SSO Enforcement: Okta, Azure AD, Google
- Network Security: Admin-Controlled Egress (Webhooks)
- Priority Support: Dedicated SLAs & Onboarding
Data Sovereignty
- Zero Telemetry Guarantee
- Shared Responsibility Model
- Audit Logs for Splunk/Datadog
- Security & Compliance Guide →
Feature Comparison
| Feature | Standard | Pro | Enterprise |
|---|---|---|---|
| Price | $49 | $99 | Custom |
| Microphone Dictation | |||
| Audio File Transcription | |||
| Video File Transcription | |||
| Batch Processing | |||
| Subtitle Export (.srt) | |||
| Speaker Diarization | |||
| JSON Data Export | |||
| MDM Deployment | |||
| SSO / SAML | |||
| Priority Support |
How it works
Three simple steps to transcribe your voice
Press the hotkey
Press ⌥+Space anywhere on your computer to start recording
Speak naturally
Talk at your normal pace. LocalWhisper captures everything.
Text appears instantly
Release the hotkey and your words appear at your cursor. Done.
Privacy by design
Your voice deserves privacy. Every word is processed entirely on your device. No servers, no cloud, no exceptions.
No Account Required
Download and start using immediately.
No Telemetry
Zero analytics, crash reports, or usage tracking. We don't know you exist.
Local History
Transcription history is stored locally on your computer. Your data never leaves your device.
GDPR & HIPAA Compatible
Perfect for professionals handling sensitive data. PHI never leaves your device.
Data Sovereignty
Processing happens 100% locally on your device. Transmission only occurs if you explicitly configure it (Enterprise tier only).
