Glossary
Voice assistant
A voice assistant is software that listens for a spoken request, works out what you want, and then acts or answers, such as setting a timer or turning off a light. Dictation is different: it turns your speech into text for you to edit.
Updated October 17, 20263 cited facts, each traced to its source
Also called virtual assistant, digital assistant, smart assistant.
A voice assistant is a program that takes a spoken request and responds by doing something: answering a question, starting a timer, sending a message or controlling a device. The key word is doing. The output is an action or a spoken reply, not a document, and the words you say are only the input.
A voice assistant acts on what you say
Most voice assistants run the same chain of steps. A microphone captures speech, a recognizer turns it into words, the system works out what you want, and then it either runs the matching action or speaks a reply. The last step is what separates an assistant from a transcription tool.
Apple describes Siri on a Mac as an intelligent assistant that is built into the computer and helps you get things done 1. The same idea applies across hardware. Google says Google Assistant keeps responding to Hey Google on non-mobile devices, including smart displays, smart speakers, TVs and cars 2.
Typical requests are commands and questions
Typical requests are short and end in an action:
- "Set a 10-minute timer in the kitchen."
- "What is 15 percent of 84?"
- "Turn off the living room lights."
- "Text my sister that I'm running late."
Each of these asks the assistant to do something or to look something up. Nothing in them is meant to appear in an email or a report. The features differ between products, so check the vendor's list of supported requests for your device before relying on one.
Why the difference matters for dictation
Dictation puts your words on the page. An assistant decides what to do with them. Apple keeps the two as separate controls: its Mac help tells you to turn Dictation on or off in Keyboard settings, a separate control from the Siri settings 3.
That split matters when you type. Dictating a paragraph should not trigger a command, and asking a question should not paste the answer into your document. When you choose a tool, ask whether it is meant to write your words or to carry out your requests. Our guide to the difference covers the common assistants, and the overview of speech to text AI places both in context.
Related terms
- Voice command: one spoken instruction that an assistant acts on.
- Wake word: the phrase that switches many assistants from waiting to listening.
- Intent recognition: the step that decides what a request asks for.
- Voice agent: an assistant that holds a longer conversation and completes multi-step tasks.
- Dictation: speech to text for writing your own words.
Guides on this topic
Evidence
Every number on this page, with where it comes from. Open a fact to see the exact words in its source.
- 1.
- 2.
- 3.
Related terms
- Speech to Text AI: Dictation, Assistants and Voice AgentsThe topic this term belongs to
- AI text detectorAn AI text detector is software that estimates whether a passage was written by a language model, usually from the words alone. Detectors make mistakes in both directions, so a score is weak evidence about how a text was made.
- Generative AIGenerative AI is the class of AI models that create new content, such as text, audio or images, from patterns in their training data. The NIST profile defines it as models that emulate the structure and characteristics of input data to generate derived synthetic content.
- Generative error correction (GER)Generative error correction (GER) passes a speech recognizer's output, often its N-best list of alternative transcripts, to a large language model, which rewrites the transcript to fix errors. It can recover words the recognizer never offered, but it can also change words that were already right.
- Intent recognitionIntent recognition is the step that decides what a spoken request is asking for, such as setting a timer or sending a message, and which details the action needs. Voice assistants and voice agents rely on it before they act.
- Large language model (LLM)A large language model (LLM) is a language model with a very large number of parameters, trained on huge amounts of text to predict and generate language. Google's glossary defines the minimum as a language model having a very high number of parameters.
- Machine learningMachine learning is a method in which a program learns its behavior from example data rather than from rules written by hand. Google's glossary defines it as a program or system that trains a model from input data.
- Prompt (AI)In AI, a prompt is the input you give a model to get a response, such as a question, an instruction or pasted text. Google's glossary defines it as any text entered as input to a large language model to condition the model to behave in a certain way.
- Speech language modelA speech language model (speech LLM) is a large language model that accepts audio as input, so it can process speech directly instead of working only on a text transcript. The 2023 SALMONN model is one example that lets an LLM process general audio inputs.
- Speech-to-speech modelA speech-to-speech model takes audio in and produces audio out with one model, without writing the conversation out as text in between. Most voice systems instead chain speech recognition, a language model and speech synthesis.
- Text to speech (TTS)Text to speech (TTS), also called speech synthesis, is software that converts written text into spoken audio. Modern systems use neural networks, and they can run on the device or in the cloud.
- Turn detectionTurn detection is the step that decides when a speaker has finished a turn, so a voice system knows when to respond. A pause can be a hesitation rather than an ending, so the decision trades speed against cutting the speaker off.
- Voice agentA voice agent is a voice system that listens, reasons with a language model, uses tools, and speaks back across several turns to finish a task, such as checking an order and rescheduling it. Benchmarks show that agents still fail many tasks on realistic audio.
Pages that use this term
- Speech to Text AI: Dictation, Assistants and Voice AgentsTopic
- Voice Assistants vs Dictation: Siri, Alexa, GeminiGuide
- Home Assistant Voice: Speech to Text and Voice CommandsGuide
- Are smart speakers still popular?Question
- Can Siri, Alexa or Gemini take long dictation?Question
- Can you control Home Assistant with Alexa or Google Assistant voice commands?Question
- Does Home Assistant voice control work offline?Question
- Does speech recognition work if you stutter?Question
- How do you turn on Hey Google?Question
- Is Gemini replacing Google Assistant?Question
- What is Alexa+ and what can it do?Question
- What is the best voice commands assistant app?Question
- What is the Bixby dictation app?Question
- What is the Home Assistant Voice Preview Edition?Question
- What voice commands does Google Assistant understand?Question
- What voice commands does Home Assistant understand?Question
- Which Google Assistant features does Gemini not support?Question
- Which is the smartest AI voice assistant?Question
- Intent recognitionGlossary
- Voice agentGlossary
- Wake wordGlossary