By Denys MedvedievGuide
Voice to text in Ghost editor
Ghost has no built-in dictation in its Koenig editor. The fix is a system-wide tool: press a hotkey, speak, and the transcript pastes at your cursor in any Ghost card. Your OS dictation works too, for short captures.
Last updated: June 2026
Voice to text in the Ghost editor works through a system-wide tool, not Ghost itself. The Koenig editor has no built-in dictation. The fix is a tool like Whisper: press a hotkey, speak, and the transcript pastes at the cursor in any Ghost card. Your operating system's dictation works too, for short notes.
I run a small newsletter on Ghost, and most of a post is one long stretch of plain prose before any cards or images get involved. The one thing I kept wanting was to talk a paragraph into the editor instead of typing it. So I went hunting for the setting. There is no setting. The Koenig editor does not have a microphone button, and after a fair bit of digging through the editor and the docs, I'm confident it isn't hiding one.
People search for "voice to text in Ghost editor," find nothing in the writing screen, and assume they missed a toggle behind a slash command. They didn't. The toggle was never built. The good news is the fix takes about two minutes, runs fully offline if you want it to, and works in every other app you open as a bonus.
Here's the thing most pages chasing this keyword won't say plainly. A Ghost paragraph card is just a text box, the same as Gmail or a search bar. Dictation that pastes at your cursor doesn't care that the box happens to be the Koenig editor.
So the real question isn't "how do I turn on voice typing in Ghost." There's no switch. The question is "which dictation tool do I run on top of the editor," and the answer depends on whether you draft in the browser admin or a desktop wrapper, and whether you want free-and-built-in or one offline hotkey that behaves the same everywhere. I'll walk all of it, set one up in two minutes, and tell you when to skip the dedicated route.
Does the Ghost editor have built-in dictation?
No. The Ghost editor — Koenig, the one built on React and Lexical — has no built-in speech-to-text, dictation, or voice-typing feature for writing into a card by voice. There's no microphone button on a paragraph, no voice command behind the slash menu, no hidden preference in the post settings. If you've been combing the editor for it, you can stop. It isn't there.
What Koenig does have is markdown parsing and a slash menu, and this is where people get turned around. You can type `#` for a heading or `/` to drop in an image, bookmark, or embed card, and the editor formats it on the fly. That's keyboard-driven formatting, not dictation. It shapes text you've already typed; it doesn't listen to you and type for you. There are also third-party dictation tools that advertise Ghost support, which is the tell that Ghost itself doesn't ship the feature — if it did, nobody would need a bolt-on.
Worth one sentence so you don't chase it on the wrong device: Ghost's admin is a web app, so on a phone you'd just use your keyboard's microphone, which dictates into any field including a Ghost card. On the desktop where most people actually draft long posts, you need a tool that sits on top of the editor. There are a couple of honest routes, and the rest of this guide covers them.
Press a hotkey, talk, text lands in the card
This is the whole mechanic, and it's boring in the best way. You press a hotkey, you speak, you release, and the transcript pastes at your cursor, in whatever text field has focus. Whisper holds a short tail after you let go of the key, so your last word doesn't get clipped. Because it pastes at the OS cursor, a Ghost paragraph card is just "any text box." Browser admin or a desktop wrapper around it, same behaviour.
That's the part the bolt-on landing pages overcomplicate. There's no integration to install into Ghost, no admin API token to paste, no webhook to babysit. Your cursor is in a card, you talk, the words appear in the card. A small capsule shows up while you speak so you know it's listening:
The hotkey is the one thing worth getting right up front. On Windows it's Ctrl+Space; on Mac it's Command+Option, a modifier-only push-to-talk you hold while speaking. Both are changeable in Settings if they clash with something you already use — and on Ghost they're worth checking, because the editor already claims Ctrl+B, Ctrl+I, and a stack of Ctrl+Option combos for headings. (My younger daughter once told me a hotkey "didn't work" in her drawing app. It was a conflict, not a bug, which is how I learned the average person has no idea what a hotkey conflict even is. So now every hotkey is customisable.) If you've ever set up dictation on Windows or on Mac, this is the same muscle memory pointed at a different app.
Set it up in two minutes (Windows or Mac)
You need a Mac on Apple Silicon or a Windows 10-or-newer PC, a working microphone, and your Ghost admin open in either a browser or a desktop wrapper. The whole local pipeline is free for any signed-in account, with no payment method asked for at sign-up. Here's the sequence.
Step 1 — Install Whisper and sign in.
Download from the download page, install, and create a free account. No card. The whole local transcription pipeline opens right away.
You'll know it worked when the app's tray icon appears and the setup wizard offers to pick a model.
Step 2 — Pick a transcription path.
The app doesn't choose for you. You get three: Cloud (OpenAI, bring your own key), Local Parakeet, or Local Whisper. For drafting posts, start local — more on that two sections down.
You'll know it worked when a model finishes downloading and shows as ready.
Step 3 — Confirm your hotkey.
Windows defaults to Ctrl+Space, Mac to Command+Option held as push-to-talk. On Mac, grant the Accessibility permission when prompted; without it, the paste-at-cursor can't reach your browser or the editor.
You'll know it worked when a test recording pastes into any text field.
Step 4 — Put your cursor in a Ghost card and talk.
Open a draft, click into a paragraph card, hold the hotkey, say a sentence, release. The transcript appears where the cursor is, in the card.
You'll know it worked when your spoken sentence is sitting in the Ghost editor as text.
The slow part is the model download, not the setup. Everything else is the four steps above. Once it's running, drafting a post stops being a typing task and starts being a talking task — which, for a 1,200-word newsletter, is the difference between an evening and a coffee break.
Browser admin vs. a desktop wrapper
Ghost's admin is a web app, so the obvious question is whether dictation behaves differently when you draft in a browser tab versus a desktop wrapper around that same admin. The honest answer: it doesn't, because a system-wide hotkey pastes at the OS cursor, and the OS doesn't care whether the cursor is in Chrome, Safari, or an Electron-style shell pointed at your Ghost site. Same key, same paste, same Koenig card on the other end.
That's the quiet advantage over the bolt-on tools that hook one specific surface. Some dictation extensions work only inside the browser; some menu-bar tools speak only into the app they were built for. A system-wide tool sidesteps the question entirely — the key that fills your Ghost paragraph also fills your Gmail compose box, a Slack reply, and a commit message. You don't relearn anything when you tab away from the editor to answer a comment or update your site copy.
So pick the writing surface you already like. If your whole Ghost workflow lives in a pinned browser tab, dictate there. If you prefer a dedicated desktop window so the editor isn't one tab among thirty, dictate there. The dictation layer is identical either way, which is the entire point of doing this at the OS level instead of inside Ghost.
Local or cloud: which mode for drafting posts
For drafting in Ghost, try local mode first. Most of what you dictate into a post is just prose — a section you're thinking through, an intro you'll edit twice anyway. It doesn't need a server in the loop, and a draft you haven't published is precisely the kind of text I'd rather not route through someone's API on the way to my own editor. If your Mac is Apple Silicon or your PC is from the last few years, local handles everyday drafting without complaint, and cloud becomes the escape hatch rather than the default.
Here's how the three paths differ, because the app makes you pick and I'd rather you pick well:
- Local Parakeet — NVIDIA's TDT engine, around 600 MB, and the fastest local option — 5 to 10 times faster than Whisper on CPU. Covers English plus 24 other European languages, 25 in total. No translate-to-English. If you write your posts in English or another European language, this is the quick, fully offline pick.
- Local Whisper — slower than Parakeet on the same machine, but the multilingual builds cover 99 languages and can translate to English. The English-only builds are English-only, not 99. Pick this if you blog in Chinese, Japanese, Korean, or any language Parakeet can't do, or if you want translation. Default English model is around 480 MB.
- Cloud (OpenAI, BYOK) — best accuracy and web access, using your own OpenAI key billed straight by OpenAI. Transcription runs on gpt-4o-mini-transcribe by default. Needs internet, so it's the one path that leaves your machine. The Cloud surface is part of Whisper Pro.
The boring truth is that for the kind of prose most people draft into a blog post, local is plenty. Both local engines run fully on your machine with nothing sent to a server. Cloud earns its place when you want top-tier accuracy on a tricky recording or you need the model to pull a fact off the web mid-sentence. For a regular publishing habit, start local and only reach for cloud when local leaves you wanting.
Drafting a post by voice, then cleaning it up
Raw dictation comes out as a run-on. You say "okay so the intro should explain why most newsletters lose readers in the first paragraph and then promise the fix," and that's the unpunctuated wall any speech engine hands you. Cleaning it up is where the paths diverge, and for a long post it's the part that actually matters.
Windows Voice Typing adds punctuation as you speak, and macOS Dictation handles basic punctuation when you say "comma" or "period." For heavier cleanup — stripping the "ums," fixing the run-ons, turning a spoken ramble into a paragraph you'd actually keep in a published post — Whisper can run an AI pass. Say the activation phrase "Hey whisper" and the text gets enhanced before it lands. On a local model that runs through Ollama; in cloud mode it's gpt-5-mini by default.
okay so the intro should explain why most newsletters lose readers in the first paragraph um and then promise the fix before the fold
The intro should explain why most newsletters lose readers in the first paragraph, then promise the fix before the fold.
For Ghost's own structure — headings, the slash-menu cards, bookmarks and embeds — the honest answer is that voice gets you the prose and Koenig's own shortcuts get you the structure. Dictate the paragraph, then type `#` for a heading, `/image` for a picture, or `>` for a quote the way you always do. No dictation tool conjures a Ghost card into existence on command; anyone promising "say insert image card and watch it appear" is selling you a demo, not a Tuesday. Get the words down fast by voice, shape the post with the shortcuts you already know.
That same speak-then-clean flow pays off well beyond your blog — you can also dictate clean prose into any app with the one hotkey, so a long section becomes a few spoken sentences instead of a paragraph you grind out by hand.
When to skip a dictation tool for Ghost
Sometimes the right tool is the free one already on your machine, and pretending otherwise would be dishonest. If you only drop short bits into Ghost — a quick title tweak, a one-line caption, an excerpt — your operating system covers it for nothing.
On Windows, press Windows key + H and the built-in Voice Typing bar opens wherever your cursor is, a Ghost card included. It punctuates on its own and is fine for short bursts. The catch: it routes through Microsoft's servers and needs an internet connection, so it isn't an offline option. On Mac, Dictation lets you speak to enter text anywhere you can type, set up in System Settings under Keyboard, and on Apple Silicon general text can be processed on-device. For a sentence here and there, both are genuinely good enough, and I'm not going to pretend a 1,200-word essay and a one-line caption need the same tool.
Reach for a dedicated, system-wide tool when the built-ins start hurting: drafting whole posts, multilingual writing, offline privacy, or wanting one hotkey that behaves the same in Ghost, your email, and your editor. Below that bar, use what's free. I'm not going to tell you to install an app for a one-line excerpt.
The same trade-off shows up if you draft long-form somewhere else first — the logic in dictating into Notion is identical, because there too the cursor, not an integration, is the real connection to the editor.
Ghost never shipped a microphone button in Koenig, and after writing this I'm fairly sure it never will. It doesn't need to, because the cursor is the integration. Talk into the card, get prose, shape the post with the shortcuts you already know. I dictated most of this guide into a text box that wasn't Ghost, with a tool that doesn't care which box it is, then pasted the lot into a draft. That's the whole trick.
Try it in your next Ghost draft
Hold the hotkey, talk, release. The transcript lands in whatever card your cursor is in — and in every other app too.
Free local mode for any signed-in account. No card required to start.
