Glossary
Voice coding
Voice coding, also called programming by voice or coding by voice, is writing and editing source code by speaking instead of typing. It needs a speech-recognition engine and a separate platform that turns spoken words into code editing actions.
Updated October 17, 20262 cited facts, each traced to its source
Also called programming by voice, coding by voice.
Voice coding is programming with speech. You say a name, a symbol or a command, and the software types it or edits the code for you. The terms programming by voice and coding by voice mean the same thing.
Voice coding needs two kinds of software
A speech-recognition engine turns sound into words, the same job that dictation does. Voice coding also needs a second program that turns those words into code actions. Nature's 2018 feature on the subject put it directly: coding by voice command requires two kinds of software, a speech-recognition engine and a platform for voice coding 1. The second program is what makes a spoken word such as "select" act on the code instead of appearing as text.
Two tools used for this are Talon Voice, a platform for hands-free input, and Cursorless, a spoken language for editing code that runs on Talon.
It often starts with a need to avoid the keyboard
Many people learn voice coding because typing hurts or is difficult. In a 2025 account, a software engineer with severe hand pain wrote that they found success with voice coding in two weeks, using four tools 2. An individual account like this is not a measure of how many people succeed, but it shows why the practice matters for accessibility.
A typical session mixes three kinds of speech
A session usually mixes three kinds of input. Plain words name variables and functions. Symbols and punctuation are spoken as short words. Commands select, move, delete or change a piece of code. Ordinary dictation covers the first two. The third needs a platform that understands the structure of the code, which is why voice coding is more than dictation with a larger vocabulary.
Why it matters for dictation and typing
For a writer, dictation is the goal. For a programmer, voice coding is the goal, and dictation is one part of it. The two are often combined: people speak prose into a chat window or a comment, use voice commands to edit the code itself, and type where precision matters.
Voice coding is different from vibe coding. In voice coding you still write and edit the code yourself, by voice. In vibe coding an AI writes the code from your description, which you may speak. The guide to voice coding explains the setup, and the guide to voice input for Claude Code, Cursor and AI coding tools covers the case where your voice goes to an AI assistant.
Related terms
- Talon Voice: hands-free input software used for voice coding.
- Cursorless: a spoken language for structural code editing.
- Voice command: a spoken phrase that makes the software act instead of type.
- Vibe coding: building software from AI-written code, described in plain language.
Guides that cover it
Evidence
Every number on this page, with where it comes from. Open a fact to see the exact words in its source.
- 1.
- 2.
Related terms
- Voice Typing in Google Docs, Word and Every Other AppThe topic this term belongs to
- Connected experiences (Microsoft 365)Connected experiences are Microsoft 365 features backed by cloud services, and Dictate is one of the experiences that analyze your content. You can turn them off in Manage Settings, but that setting also turns off other services.
- CursorlessCursorless is a spoken language for structural code editing that lets developers code by voice. Every command is an action performed on a target in the code, and it runs on Talon with a VS Code extension.
- Dictate (Microsoft 365)Dictate is the speech-to-text feature in Microsoft 365 apps such as Word, Outlook and PowerPoint. It needs a Microsoft 365 subscription, a microphone and a reliable internet connection.
- Dictation (ChromeOS)Dictation on ChromeOS is a built-in accessibility feature that types recognized speech into an editable field. You turn it on with Search + D or the microphone icon in the status tray.
- Site microphone permissionSite microphone permission is the browser's setting for each website that decides whether that site may use your microphone, usually chosen when the browser prompts you. It works alongside the operating system's own microphone setting, so both must allow the microphone before a site can listen.
- Talon VoiceTalon Voice, usually called Talon, is hands-free input software for writing, coding, browsing and gaming. It runs alongside a speech-recognition engine, and it is used for voice coding, often together with the Cursorless editing language.
- Text insertionText insertion is the step where dictation software places recognized words into the text field that has the cursor. It is done either by simulating keystrokes or by pasting the text from the clipboard.
- Transcribe (Microsoft 365)Transcribe is a Word for Microsoft 365 feature that turns an uploaded audio file into text in the Transcribe pane, rather than typing your speech into the document. Its monthly limits depend on your license.
- Vibe codingVibe coding is building software by describing what you want to an AI model and accepting the code it writes, without reviewing that code. Andrej Karpathy introduced the term, and the developer Simon Willison argues for a narrower meaning than the broad one now in use.
- Voice typing (Google Docs)Voice typing in Google Docs is a built-in speech-to-text tool that types as you speak. You start it from the Tools menu in a supported browser, and the browser controls the speech-to-text service.
- WaylandWayland is the display system that Linux desktops are moving to in place of the X Window System, called X11. Its compositor delivers input to each app, so a typing tool that worked on X11 may not type on a Wayland desktop.
- Web Speech APIThe Web Speech API is a set of browser interfaces that let a web page start speech recognition and receive the recognized words as text, through an object called SpeechRecognition. Where the recognition runs, on your device or on a server, depends on the browser.