# Dictation, plainly defined.

Canonical page: https://flit.fyi/glossary

> 47 dictation and speech-to-text terms, from push-to-talk to word error rate, each defined in plain language with the practical context that matters and links to where it shows up in Flit.

The vocabulary of speech-to-text, one page per term: what it means, why it matters in practice, where the marketing tends to blur it, and where you can see it working.

## On your Mac

The settings, keys and features in macOS that dictation runs into, and where each one is.

- [Globe key (Fn key, Function key)](https://flit.fyi/glossary/globe-key): The Globe key is the key marked with a globe symbol, and usually also with fn, on Mac keyboards.
- [Voice Control (Mac voice commands)](https://flit.fyi/glossary/voice-control): Voice Control is an accessibility feature built into macOS that lets you operate a Mac entirely by voice.
- [Dictation commands (Mac dictation commands, voice punctuation commands)](https://flit.fyi/glossary/dictation-commands): Dictation commands are the words and phrases you say while using Dictation on a Mac to enter punctuation, symbols, capital letters, and formatting instead of ordinary text.
- [Auto-punctuation (automatic punctuation)](https://flit.fyi/glossary/auto-punctuation): Auto-punctuation is a setting of Dictation on Mac that automatically inserts commas, periods, and question marks as you dictate.
- [Input volume (microphone volume, input level, mic gain)](https://flit.fyi/glossary/microphone-input-volume): Input volume is the setting on a Mac that controls how strongly sound from the selected microphone or other input device is captured.
- [Mic Mode (Mic Modes, Voice Isolation, Wide Spectrum)](https://flit.fyi/glossary/mic-mode): Mic Mode is a macOS control that changes how your Mac’s microphone treats the sound around you in apps that support it.
- [Secure Keyboard Entry (Secure Event Input, secure input)](https://flit.fyi/glossary/secure-keyboard-entry): Secure Keyboard Entry is a Terminal setting on a Mac that prevents other apps on your computer or the network from detecting and recording what you type in Terminal.
- [Live Captions (real-time captions, live transcription)](https://flit.fyi/glossary/live-captions): Live Captions is a macOS accessibility feature that shows a real-time transcription of spoken audio in a window on your screen, for audio in any app and for live conversations around you.
- [Enhanced Dictation (Use Enhanced Dictation, offline dictation)](https://flit.fyi/glossary/enhanced-dictation): Enhanced Dictation was a checkbox in the Dictation pane of Keyboard preferences on older versions of macOS that downloaded speech recognition software to the Mac so you could dictate offline.
- [Improve Siri & Dictation (Share Audio Recordings, Siri & Dictation History)](https://flit.fyi/glossary/improve-siri-and-dictation): Improve Siri & Dictation is an opt-in privacy setting that lets Apple store and review a sample of the audio from your Siri and Dictation interactions to develop and improve those features.
- [Apple Intelligence](https://flit.fyi/glossary/apple-intelligence): Apple Intelligence is Apple’s set of generative AI features built into macOS, including Writing Tools for rewriting, proofreading and summarizing text.
- [SpeechAnalyzer (SpeechTranscriber, Speech framework)](https://flit.fyi/glossary/speechanalyzer): SpeechAnalyzer is a class in Apple’s Speech framework, introduced with macOS 26 and iOS 26, that apps use to turn spoken audio into text.

## Talking to it

The words for how dictation starts, stops, and reaches the app you are in.

- [Dictation](https://flit.fyi/glossary/dictation): Dictation is producing written text by speaking, with the words transcribed in or near real time at the place you are writing.
- [Voice typing](https://flit.fyi/glossary/voice-typing): Voice typing is another name for dictation: entering text into an application by speaking instead of using the keyboard.
- [Transcription (file transcription)](https://flit.fyi/glossary/transcription): Transcription is converting an existing audio or video recording into text after the fact.
- [Push-to-talk (hold-to-talk)](https://flit.fyi/glossary/push-to-talk): Push-to-talk is an activation style where recording runs only while a key is held down: press, speak, release, done.
- [Voice activity detection (VAD)](https://flit.fyi/glossary/voice-activity-detection): Voice activity detection (VAD) is the technique of detecting when someone is speaking versus when there is silence or background noise.
- [Wake word (hotword)](https://flit.fyi/glossary/wake-word): A wake word is a spoken phrase that turns a listening device on, like "Hey Siri" or "Alexa".
- [Accessibility permission (Accessibility access)](https://flit.fyi/glossary/accessibility-permission): Accessibility permission is the macOS setting that lets one app read and control the interface of other apps.

## How it hears you

The models, the measurements, and the failure modes of turning audio into words.

- [Speech-to-text (STT)](https://flit.fyi/glossary/speech-to-text): Speech-to-text (STT) is the technology that converts spoken audio into written words.
- [Automatic speech recognition (ASR)](https://flit.fyi/glossary/automatic-speech-recognition): Automatic speech recognition (ASR) is the machine-learning field, and the class of models, that turns audio of human speech into text.
- [Whisper](https://flit.fyi/glossary/whisper): Whisper is a family of open-source speech recognition models released by OpenAI in 2022, trained on 680,000 hours of audio and covering about 99 languages.
- [Parakeet](https://flit.fyi/glossary/parakeet): Parakeet is a family of open-source speech recognition models from NVIDIA, built on a transducer architecture, which can emit words as audio arrives.
- [Neural Engine (ANE)](https://flit.fyi/glossary/neural-engine): The Neural Engine is the part of an Apple silicon chip built to run machine-learning models efficiently, alongside the CPU and GPU.
- [Streaming transcription (real-time transcription)](https://flit.fyi/glossary/streaming-transcription): Streaming transcription shows words on screen while you are still speaking, rather than after you stop.
- [Language identification (LID)](https://flit.fyi/glossary/language-identification): Language identification is the step where speech software works out which language is being spoken before, or while, it transcribes.
- [Word error rate (WER)](https://flit.fyi/glossary/word-error-rate): Word error rate (WER) is the standard measure of speech recognition accuracy: the number of words a model got wrong, divided by the number of words actually spoken.
- [Hallucination](https://flit.fyi/glossary/hallucination): In speech recognition, a hallucination is text the model produces that nobody said: a plausible phrase invented from silence, noise, or a fragment too short to transcribe.
- [Latency (key-up latency)](https://flit.fyi/glossary/latency): In dictation, latency is the time between the end of your speech and finished text appearing at the cursor.
- [Speaker diarization (speaker labels)](https://flit.fyi/glossary/speaker-diarization): Speaker diarization is the process of working out who spoke when in a recording, so a transcript can be labeled by speaker.
- [Whisper large-v3 turbo (Whisper turbo, large-v3-turbo)](https://flit.fyi/glossary/whisper-large-v3-turbo): Whisper large-v3 turbo is a speech recognition model from OpenAI, released on 1 October 2024.
- [Cohere Transcribe (cohere-transcribe-03-2026)](https://flit.fyi/glossary/cohere-transcribe): Cohere Transcribe is an open-source speech recognition model from Cohere, released in March 2026.
- [Qwen3-ASR (Qwen3-ASR-1.7B, Qwen3-ASR-0.6B)](https://flit.fyi/glossary/qwen3-asr): Qwen3-ASR is a family of open-source speech recognition models from Alibaba’s Qwen team, released on 29 January 2026.
- [MLX (Apple MLX, MLX framework)](https://flit.fyi/glossary/mlx): MLX is an open-source array framework for machine learning on Apple silicon, made by Apple’s machine learning research team.
- [Core ML (CoreML, Apple Core ML)](https://flit.fyi/glossary/core-ml): Core ML is Apple’s framework for running machine learning models inside an app, on the device.
- [Quantization (model quantization, 4-bit, 8-bit)](https://flit.fyi/glossary/quantization): Quantization is storing a model’s numbers with fewer bits each, for example 4 or 8 bits where the original used 16 or 32.
- [Real-time factor (RTF, RTFx)](https://flit.fyi/glossary/real-time-factor): Real-time factor (RTF) is the time a speech recognition system takes to process audio, divided by the length of that audio.

## What comes out

Everything that happens between a raw transcript and text you would have typed.

- [Disfluency (fillers)](https://flit.fyi/glossary/disfluency): A disfluency is any break in fluent speech: fillers like "um" and "uh", repeated words, false starts, and self-corrections.
- [Formatting pass (post-processing)](https://flit.fyi/glossary/formatting-pass): The formatting pass is the step after speech recognition that turns a raw transcript into text a person would have typed: punctuation, capitalization, numbers as digits, fillers removed, and a tone suited to where the text is going.
- [Verbatim mode](https://flit.fyi/glossary/verbatim-mode): Verbatim mode is a dictation setting where the output is exactly what you said, with no rewording, tone adjustment, or cleanup beyond basic recognition.
- [Spoken punctuation (voice commands)](https://flit.fyi/glossary/spoken-punctuation): Spoken punctuation is saying the name of a mark or symbol, like "comma", "open paren", or "new paragraph", and having the dictation tool type the symbol instead of the word.
- [Text expansion (snippets)](https://flit.fyi/glossary/text-expansion): Text expansion replaces a short trigger with a longer saved text: an address, a signature, a canned reply.
- [Personal dictionary (custom vocabulary)](https://flit.fyi/glossary/personal-dictionary): A personal dictionary is the list of words a dictation tool has been taught to spell your way: names, products, jargon, and anything the speech model would otherwise write as the most probable English.
- [Tone matching (register)](https://flit.fyi/glossary/tone-matching): Tone matching is a formatting feature that writes the same dictated words differently depending on where they are going: lowercase and loose in a chat app, punctuated and complete in an email, untouched in a terminal.
- [Words per minute (WPM)](https://flit.fyi/glossary/words-per-minute): Words per minute (WPM) measures text production speed.

## Where it runs

The two words that decide whether your voice becomes someone else’s data.

- [On-device processing (local processing)](https://flit.fyi/glossary/on-device-processing): On-device processing means the speech recognition model runs on your own computer, so audio is transcribed locally and never uploaded.
- [Local LLM (on-device language model)](https://flit.fyi/glossary/local-llm): A local LLM is a language model that runs on your own computer rather than on a vendor’s server.

## Your voice was always faster.

7 days free, then $19 USD once. No account, no subscription, nothing uploaded.

[Download for Mac](https://flit.fyi/download) [Buy now · $19 USD](https://flit.fyi/pricing#personal)

macOS 14 or later · Apple silicon