Privacy

On-device means on-device.

Cloud dictation is a product decision dressed up as a feature. VV’s default path is a local model on Apple Silicon. The audio you just spoke is not a training sample for someone else.

The default English model is NVIDIA Parakeet, running on your Mac via ONNX. Voice activity detection uses Silero. Optional Whisper-family models are Apache-2.0. None of that requires a VV login.

Transforms are separate. They can stay on the Mac with Apple Intelligence or Ollama. If you point one at OpenAI, Anthropic or Groq, that Transform says so on its face. Standard dictation does not follow it out the door.

See also on-device speech-to-text, privacy, and VV vs Wispr Flow.