Home/Docs/How transcription works

How transcription works

Five stages between holding a key and seeing text. Four of them never touch a network, and the fifth only does if you have explicitly turned cleanup on.

The pipeline

  1. Capture. While the key is held, audio is recorded at 16 kHz mono directly into memory. Nothing is written to disk.
  2. Transcribe. On release, the buffer is passed to Whisper running locally through WhisperKit, which uses your Mac's Neural Engine and GPU. The audio is discarded once text exists.
  3. Expand snippets. If what you said matches a snippet trigger exactly, the expansion is inserted immediately and the remaining steps are skipped.
  4. Clean up (optional). Only if you have enabled AI cleanup. This is the one stage that can involve a network, and only the text is ever sent.
  5. Insert. The result is placed at your cursor — see How text is inserted.

Live partial transcripts

While you hold the key, the app re-transcribes the growing buffer roughly three times a second so words appear in the HUD as you speak. This is a preview, not the final answer: the real pass runs on the complete recording after you release, and it is the one that gets inserted. Seeing partials that later change slightly is normal and expected — the full recording gives Whisper more context to work with.

Partials cost a little extra compute. If you are on an older Mac and want maximum battery life, turn off Show words as you speak in Settings.

What needs a network

StageNetwork
Capturing audioNever
TranscribingNever — after the one-time model download
Snippet expansionNever
AI cleanupOnly if enabled and pointed at a cloud provider. Local Ollama and “off” stay on your Mac.
Inserting textNever

With cleanup off — the default — dictation works in airplane mode indefinitely.

Why results vary

Whisper predicts the most likely word sequence given the audio and its training. That explains most of what you will observe: it is excellent on ordinary prose, good with accents on larger models, and unreliable on proper nouns it has never seen. The fix for names is not a bigger model but the personal dictionary.

A known Whisper quirk

On near-silent or very short audio, Whisper models occasionally emit a stock phrase such as “Thank you” or “Thanks for watching” — an artifact of the subtitled video in their training data. Push-to-talk avoids most of it, since you hold the key only while speaking. If you see it, that is the model, not a fault in your setup.

Documentation for OpenVoiceFlow 0.5.5 · last updated 2026-07-31. Something wrong or missing here? That is a bug — tell us at shimoverse@gmail.com.