Voice to text in Coda

Does Coda have built-in dictation?

No. Coda has no built-in speech-to-text, dictation, or voice-typing feature for writing into a doc by voice. There's no microphone button on a row, no voice command, no hidden preference. If you've been combing the settings for it, you can stop. It isn't there, and the maker community has been asking for it since 2021 without it shipping.

What does exist is a Coda Pack called ElevenLabs Voice AI, and this is where people get turned around. That Pack goes the other direction — it turns the text in your doc into spoken audio. It's text-to-speech, not speech-to-text. Useful if you want your doc read aloud; useless if you want to talk a row into a table. They sound like the same feature and are exact opposites, which is the kind of naming collision that costs an afternoon. I'd rather you skip that afternoon.

The browser extension picture is worth one paragraph so you don't chase it onto the wrong setup. There's a popular Chrome and Edge extension, Voice In, that dictates into web pages including the browser version of Coda. It works, with one structural catch: it's a browser extension, so it only reaches Coda when Coda is a tab. Open the Coda desktop app and the extension can't see it. More on that two sections down. The point for now: nothing inside Coda does this. You need a tool that sits on top of it.

Press a hotkey, talk, text lands in the cell

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 Coda table cell is just "any text box." Browser tab or the desktop app, same behaviour.

That's the part the landing pages overcomplicate. There's no Pack to install into Coda, no API token to paste, no automation to babysit. Your cursor is in a cell, you talk, the words appear in the cell. 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. (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 Coda open in either the desktop app or a browser tab. The whole local pipeline is free for any signed-in account, with no payment method asked for at sign-up. Here's the sequence.

The slow part is the model download, not the setup. Everything else is the four steps above. Once it's running, filling a row in a Coda table stops being a typing task and starts being a talking task.

voice to text on Windows · on Mac

Coda in the browser vs. the desktop app

Coda ships two ways — a browser version and a desktop app for Mac and Windows — and which dictation route works depends on which one you use. Most pages ranking for this keyword point you straight at Voice In, the Chrome and Edge extension. It's a fine pick with one structural limit: it's a browser extension, so it only reaches Coda when Coda is a tab in that browser. Run the Coda desktop app and the extension simply can't see the window.

A system-wide hotkey sidesteps that. It pastes at the OS cursor regardless of which window owns it, so the same key that fills a Coda cell in the browser also fills a cell in the Coda desktop app, your Gmail compose box, a Slack message, and a commit message. One tool, every text field, both the browser and the native app. You don't relearn anything when you switch, and you don't need a different solution depending on how you happen to have Coda open today.

If you only ever touch Coda in a browser tab and never the desktop app, the extension is a tidy, focused option and worth a look. The moment you use the Coda desktop app, or you want the same flow across every program you open, the system-wide route wins. I'd reach for the one hotkey because I switch apps roughly forty times an hour and don't want forty different dictation buttons to remember.

Local or cloud: which mode for your docs

For most Coda work, try local mode first. A lot of what lands in a Coda doc is the kind of thing you'd rather not pass through a vendor's logs — a project plan, a client note, a half-formed idea in a table. If your Mac is Apple Silicon or your PC is from the last few years, local handles everyday dictation 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 work 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 for Chinese, Japanese, Korean, or any translation work, which Parakeet can't do. 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 text most people put in Coda, 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 hard recording or you need the model to pull a fact off the web mid-sentence. For a daily doc habit, start local and only reach for cloud when local leaves you wanting.

Punctuation, cleanup, and Coda formatting by voice

Raw dictation comes out as a run-on. You say "okay so add a row review the launch doc owner is me due thursday status blocked," and that's the unpunctuated wall any speech engine hands you. Cleaning it up is where the paths diverge.

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 sentence into something you'd actually keep in a doc — 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.

For Coda's own structure — building a table, setting a column type, adding a select option, writing a formula — the honest answer is that voice gets you the text and Coda's own interface gets you the structure. Dictate the cell contents, then build the table and set the column types the way you always do. No dictation tool conjures a Coda table schema into existence on command; anyone promising "say new table with three columns and watch it build" is selling you a demo, not a Tuesday. Get the words down fast by voice, shape the doc with the controls you already know.

That same speak-then-clean flow pays off well beyond your docs — you can also dictate clean prose into any app with the one hotkey, so a long paragraph becomes a few spoken sentences instead of something you type out.

When to skip a dictation tool for Coda

Sometimes the right tool is the free one already on your machine, and pretending otherwise would be dishonest. If you only drop short captures into Coda — a quick row, a two-word status — 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 Coda cell 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. And if you only ever use Coda in a browser tab, the Voice In extension is a focused, free option built for exactly that.

Reach for a dedicated, system-wide tool when the built-ins start hurting: long notes, multilingual work, offline privacy on Windows, the Coda desktop app rather than a tab, or wanting one hotkey that behaves the same in Coda, 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 status update.

The same trade-off shows up if you also keep work in other tools — the logic in dictating into Google Docs is identical, because there too the cursor, not a plugin, is the real integration.

Coda never shipped a microphone button, 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 cell, get text, shape the doc with the controls you already know. I dictated most of this guide into a text box that wasn't Coda, with a tool that doesn't care which box it is, then pasted the lot into a doc. That's the whole trick.