VTT for Mac.

VTT for Mac

VTT is a native macOS dictation app that transforms your voice into text with the privacy of on-device processing and the flexibility of multiple speech engines. Built exclusively for Mac in Swift and AppKit, it delivers a seamless, system-native experience that feels like it shipped with macOS—while giving you complete control over where your audio goes and which engine transcribes it.

Product Highlights

• On-Device Privacy: Transcribe entirely on your Mac using Apple's Speech engine—no audio leaves your machine, no account required, no tracking ever.
• Engine Choice: Switch between Apple's on-device models and premium cloud engines (Deepgram, OpenAI, ElevenLabs) using your own API key, with per-language routing.
• Truly Native Design: Built in Swift and AppKit, not Electron—tiny, instant, and living in your menu bar with global hotkey activation and auto-insert into any app.
• Accent-Friendly: Cloud engines trained on millions of voices handle strong accents far better than built-in dictation, with automatic language detection or manual selection.
• Local History: Every transcript saved instantly to device-only history—never lose text to a misclick, with one-click re-paste from the menu bar.
• Offline Ready: Full functionality without internet when using on-device models; download languages in advance for instant activation.

Use Cases

• Professional Writing: Dictate emails, documents, and long-form content hands-free with the accuracy of cloud engines or the privacy of on-device processing.
• Multilingual Workflow: Switch languages instantly via keyboard input—speak Russian, get Russian text; switch to English, get English—no menu-diving or unwanted translation.
• Accessibility & Speed: Replace typing entirely for users with repetitive strain injuries or anyone who thinks faster than they type, with global hotkey activation from any app.

Target Audience

VTT is designed for Mac users who demand both privacy and performance—writers, developers, multilingual professionals, and accessibility-focused users who want dictation that respects their data while delivering accuracy competitive with cloud-only solutions.