Skip to main content

​
Local Speech Recognition

Pipit uses advanced on-device speech recognition to transcribe your voice. Your audio is processed entirely on your Mac — nothing is sent to the cloud.

​
How It Works

1

Activate

Tap your hotkey (default: Right Option) to start recording. You can also hold it for push-to-talk.
2

Speak

A subtle overlay appears showing the recording status. Speak naturally — Pipit handles punctuation and formatting.
3

Release

Tap the hotkey again to stop, or release it if you held it. Pipit then transcribes the recording.
4

Insert

The transcribed text is automatically inserted at your cursor position in any application.

​
Hotkey Gestures

Hold and Release

Hold the hotkey while speaking and release it when done. Best for quick dictations.

Tap to Toggle

Press once to start, press again to stop. Better for longer dictations where holding a key is tiring.
Both gestures are always available; there is no recording-mode setting to change.

​
Tips for Better Accuracy

  • Use a quality microphone — While built-in mics work, a USB microphone or headset improves results significantly.
  • Minimize background noise — Find a quiet space when possible for the best transcription quality.
  • Speak clearly and consistently — Natural speech works best, but enunciate at a steady volume.

​
Supported Languages

Pipit supports 25 European languages with automatic detection. Choose English Only or Multiple Languages on the Language step during onboarding. Multiple Languages automatically detects and transcribes the language you’re speaking, while English Only uses English-optimized recognition. To change modes later, open Post Processing, scroll to the bottom, click Reset Onboarding, and choose your preferred mode when you reach the Language step again.