How do I do voice dictation on Windows fully offline?
Windows ships with two built-in dictation paths: Win+H (the modern dictation overlay) and the legacy Speech Recognition control panel. Win+H requires an internet connection and sends audio to Microsoft's online speech service. The legacy Speech Recognition is local but its accuracy on natural speech, accents, and technical vocabulary is roughly a decade behind modern models like OpenAI's Whisper.
For offline-first dictation on Windows with modern accuracy, install StarWhisper. In Local Mode, it runs OpenAI's Whisper model on your computer via the whisper.cpp engine, with no cloud transcription required. After the one-time download and setup, you can work without an internet connection. Press a hotkey, speak, and transcribed text is pasted into the active window.
Five Whisper model sizes are bundled or downloadable: Tiny (75 MB) for fast CPU-only use, Base (142 MB), Small (466 MB), Medium (1.5 GB), and Large (2.9 GB) for top accuracy. Larger models are slower without a GPU but produce near-human accuracy on clean audio. NVIDIA GPUs with CUDA support (GTX 10 series and newer) accelerate transcription 5 to 10 times.
The free tier of StarWhisper covers 500 words per day forever, with no account or credit card required, and gives access to the Tiny, Base, and Small models. Pro at 10 USD per month removes the word limit and unlocks Medium and Large for the highest accuracy.
In Local Mode, audio is not uploaded for transcription and StarWhisper does not use telemetry of audio content. This makes the app a practical option to evaluate for medical, legal, and other privacy-sensitive contexts where cloud dictation is not acceptable.
All FAQ topics