Powerful Features for
Effortless Voice Input

Everything you need to transform your voice into polished text, across any application.

Multimodal AI Transcription

Powered by multimodal reasoning models that understand audio context, not just words. One-step transcription with built-in polish for natural, accurate results.

  • ~1-2s response time
  • Context-aware processing
  • Automatic detection
  • Background noise filtering

Intelligent Polish

Transcription and AI refinement happen in a single step. Grammar, punctuation, and natural flow — all handled by the multimodal engine.

  • Grammar correction
  • Smart punctuation
  • Context awareness
  • Style adaptation

Enterprise-Grade Data Protection

Inherits Vertex AI's zero data retention policy. Your audio is never stored, never used for model training, and never reviewed by humans. All transcription data is saved locally on your device.

  • Zero data retention
  • No model training use
  • No human review
  • SOC 2 / ISO 27001 / HIPAA

100+ Languages

Support for over 100 languages with automatic detection. Handles various accents, dialects, and speaking speeds with ease.

  • 100+ languages
  • Auto-detection
  • Accents & dialects
  • Continuously expanding

And Much More

Custom Hotkey

Set any keyboard shortcut to start and stop recording. Push-to-talk or toggle mode.

BYOK Mode

Bring Your Own Key - use your own API key for full control over costs and data.

Audio Ducking

Automatically lowers system audio while recording for clearer transcription.

AI Command Mode

Select text and let AI rewrite, translate, or summarize. Works in any app.

Custom Dictionary

Add names, jargon, and technical terms for better recognition accuracy.

Text Snippets

Create shortcuts that expand into longer phrases. Perfect for frequently used text.

Ready to get started?

Try Yak free for 14 days. Experience the difference.