High-speed, intelligent push-to-talk voice typing with seamless Arabic + English code-switching. Hold your hotkey, talk naturally, and watch it paste into any app.
Hold your hotkey anywhere on your system to record. Release, and your speech is immediately formatted and pasted directly into your active window.
Switch between Arabic and English fluidly mid-sentence. Understands regional dialects (Levantine, Egyptian, Gulf, Darija) alongside technical terminology.
Your API keys are sealed directly inside macOS Apple Keychain or Windows DPAPI. Zero plain-text credentials stored on disk.
Use the ultra-fast Gemini 2.5 Flash Audio endpoint for state-of-the-art formatting, or switch to embedded local Whisper for air-gapped offline privacy.
Frameless bottom status pill that lives harmoniously at the edge of your screen. Unobtrusive visual feedback that never steals focus.
Injects clean text anywhere: Slack, Notion, VS Code, Google Docs, Discord, WhatsApp Desktop, or native code editors without plugins.
Command (>300ms) anywhere to dictate!
Control (>300ms) anywhere to dictate!
FoxyFlow uses Gemini 2.5 Flash Audio API fine-tuned with smart multilingual context. Unlike standard STT that assumes a single language, it expects Arabic speakers to use English technical jargon and automatically formats numbers, punctuation, and mixed script accurately.
Yes. In cloud mode, audio buffers are sent directly to the API endpoint over encrypted TLS with zero intermediate logging. In offline mode, the audio never leaves your machine — it is transcribed entirely by embedded local Faster-Whisper.