A lightweight macOS push-to-talk dictation app that converts speech to text with Gemini. Spoken language is detected automatically, dictation works across all major languages, and translation modes can return a target-language output when you need one.
Requires macOS Monterey (12.0) or later • Free app; you only pay Google Gemini API usage, usually very low
Since SrizonVoice is not notarized by Apple yet, macOS Gatekeeper may block the app on first launch. To fix this, open Terminal and run:
xattr -cr /Applications/SrizonVoice.appThis removes the quarantine flag that macOS adds to downloaded apps. You only need to do this once.
Clean, native macOS interface that stays out of your way
Live Demo — Press the hotkey, speak, and insert the result

Dictation Controls

API Key & Permissions

Transcription Settings

Custom Gemini Output
Fast AI transcription in a simple push-to-talk app
Gemini handles transcription, correction, custom prompts, and translation in one request. Spoken language is detected automatically from the audio.
Press the hotkey once to record and again to insert text, or switch to push-to-talk when you prefer hold-to-record behavior.
Default Fn key works from any app — fully customizable in Settings. Press Escape while recording to cancel without transcribing.
Speak in all major languages without choosing a source language first. Translation modes let you choose the target output language.
Text is inserted directly into any active text field using Accessibility APIs, with enhanced support for Electron apps like Slack, Discord, Notion, and more.
Built with Swift and SwiftUI as a native macOS app. Minimal resource usage, launches at login, and stays out of your way.
The app is free. Use your own Gemini API key stored securely in macOS Keychain; you only pay Google Gemini API usage, which should be very low for typical dictation.
Three simple steps to hands-free typing
Press the Fn key (or your custom shortcut) from any app to start recording
Talk at your natural pace in any major language. Gemini detects the spoken language from the audio
Press again, or press Esc, and Gemini returns polished text or a target-language translation for insertion
Get started in under a minute
Download the DMG file and open it
Drag SrizonVoice to your Applications folder
Launch the app — it appears in your menu bar
Enter your Gemini API key, then click "Grant Permissions" to set up Microphone, Accessibility, and Input Monitoring access
Press your hotkey (default: Fn) and start dictating!
Note:You'll need to grant Microphone and Accessibility permissions in System Settings for dictation and text insertion to work.
Speak naturally without picking a source language first. Gemini detects the spoken language automatically, and translation modes can output the result in your selected target language.
🇺🇸
English
🇪🇸
Spanish
🇫🇷
French
🇩🇪
German
🇨🇳
Chinese
🇯🇵
Japanese
🇸🇦
Arabic
🇧🇩
Bengali
🇮🇳
Hindi
🇧🇷
Portuguese
🇷🇺
Russian
🇰🇷
Korean
🇮🇹
Italian
🇹🇷
Turkish
🇻🇳
Vietnamese
🇳🇱
Dutch
🇵🇱
Polish
🇹🇭
Thai
🇸🇪
Swedish
🇮🇩
Indonesian
Plus all major languages supported by Gemini
SrizonVoice respects your privacy. Audio is only captured while you are actively recording and is sent directly to Google Gemini for transcription, correction, and optional translation. No data passes through Srizon servers.
See Google Privacy Policy for Google's provider policy.
Download the free app and start typing with your voice across any macOS app today. Your only cost is Gemini API usage, which should be very low for typical dictation.
Download SrizonVoice