Type with yourVoicepowered by AI
Vox is an intelligent voice input method that transforms your speech into text instantly. Press a hotkey, speak naturally, and watch your words appear—enhanced by AI.
{
// Press hotkey to start
"hotkey": {
"toggle": ["cmd", "shift", "r"],
"mode": "toggle"
},
// AI enhancement
"llm": {
"enabled": true,
"provider": "openai",
"model": "gpt-4o-mini"
},
// Voice recognition
"asr": {
"provider": "deepgram"
}
}Vox: AI-Powered Voice Input
Stop typing. Start speaking. Vox transforms your voice into perfectly formatted text with AI enhancement—works anywhere on your system.
Voice input, reimagined
Powerful features that make voice input faster, smarter, and more natural than typing.
Hotkey Activation
Press a customizable hotkey to start recording. Hold or toggle mode—your choice. Works system-wide in any application.
AI Enhancement
Optional LLM processing cleans up transcripts, fixes grammar, adds punctuation, and formats text perfectly.
Real-time Transcription
See your words appear instantly as you speak. Multiple ASR providers supported: Deepgram, Whisper, and more.
Smart Modes
Dictation, social media, code—each mode optimizes output for different contexts with custom AI prompts.
Privacy First
Choose your ASR provider. Use local models for complete privacy or cloud services for best accuracy.
Direct Output
Text appears directly where you're typing. No copy-paste needed. Preserves clipboard and works everywhere.
Ready to ditch the keyboard?
Download Vox and experience the future of text input. Free and open source.