Voice to text in Todoist

Does Todoist have voice to text?

Yes, but for adding tasks, not for general dictation. Todoist's main voice feature is Ramble, which by its own help docs is a "voice-to-tasks feature" — you speak naturally, it listens, and it captures actionable tasks in real time. The important word is tasks. Ramble doesn't transcribe you word for word; it interprets what you say and turns it into structured tasks, pulling out dates, priorities, and durations from how you phrased them. It runs on web, macOS, Windows, iOS, Android, and even Wear OS, and the tasks land in your Inbox unless you opened it inside a specific project.

There's a catch worth knowing before you lean on it. On the free or Beginner plan, Ramble is capped at 10 sessions a month, resetting on the 1st. Each dictation counts as a session even if you decide not to keep the tasks. Upgrading to Pro or Business removes the cap. So it's genuinely useful for offloading a brain-dump of to-dos, but it's metered, and it always produces tasks — never text in the field you're editing.

The rest of Todoist's voice surface follows the same shape. Siri and Google Assistant add tasks by voice from your phone or watch, and on an Apple Watch you can dictate a task straight to your wrist. You can also record an audio comment on a task, but that attaches an audio file — it doesn't transcribe your voice into the comment as text. None of these lets you put your cursor in a description box and just talk. For that, you need a tool that types wherever the cursor is, and there's an honest free-versus-dedicated answer coming up.

Press a hotkey, talk, text lands in the field

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 operating-system cursor, a Todoist task name is just "any text box," and so is the description, and so is a comment. Desktop app or the browser version, same behaviour.

That's the part the feature comparisons overcomplicate. There's no Todoist integration to authorise, no API token to paste, no automation rule to babysit. Your cursor is in the description box, you talk, the words appear in the description box. 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 a to-do app this matters, because Todoist's own Ramble grabs Alt+Shift+R on Windows and Option+Shift+R on Mac as global shortcuts, so you'll want your dictation key to dodge those. 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 Todoist open in either the desktop app or the browser. 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, the act of writing a real task — the one with a description that actually explains what "follow up with Marcus" means — stops being a typing chore and starts being a talking task.

voice to text on Windows · on Mac

Dictating task names, descriptions, and comments

This is where the two approaches sort themselves out cleanly. For a quick task — "buy milk," "call the dentist Tuesday" — Todoist's own voice tools are the right pick, and I mean that. Ramble or Siri grabs the task, parses the date, drops it in your Inbox, and you never touched a keyboard. If that's all you do, you don't need anything else, and the next paragraph will tell you to ignore the rest of this guide.

The dictation tool earns its place the moment the field gets longer than a task name. A description that lays out the three things a task actually involves. A comment that's really a paragraph of meeting notes. A checklist of sub-steps you'd rather speak than type one Enter at a time. Ramble can't fill those — it only makes tasks. A system-wide hotkey can, because it types wherever the cursor sits. Click into the description, hold the key, talk, and the text lands in the description. Click into the comment box, do the same, and it lands there. One key, every field, including the ones Todoist's voice features don't reach — same as how the same hotkey fills a Gmail compose box or a code editor.

Between you and me, this is the split I'd actually run day to day: Todoist's Ramble for the rapid "remember to do X" captures, and the hotkey for the moment a task needs real prose behind it. They're not competitors. One adds the task; the other writes the words inside it. I switch apps roughly forty times an hour and I'm not about to learn a separate voice button for each field a task happens to have.

Local or cloud: which mode for your task notes

Try local mode first. A lot of what ends up in a Todoist description is the kind of thing you'd rather not hand to a server you don't run — a client's name, a salary figure in a hiring task, the gist of a private conversation you're following up on. Todoist's own Ramble sends your voice to its servers to do the interpreting; a local dictation tool keeps the audio on your machine. 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 write your tasks 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 a task, 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 day-to-day task notes, start local and only reach for cloud when local leaves you wanting.

Punctuation and cleanup for longer task notes

Raw dictation comes out as a run-on. You say "okay follow up with marcus about the q3 budget he wanted the revised numbers by thursday and remind him about the contract," 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 ramble into a description you'd actually keep — 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 Todoist's own structure — due dates, the @label and #project tags, p1/p2 priorities — the honest answer is that voice gets you the words and Todoist's Quick Add syntax gets you the structure. Todoist parses natural-language dates and tags when you type them into the task field: "tomorrow at 4pm," "@email," "p1." So dictate the task name, then let Todoist's own smart parsing read the date and label you spoke, or type the tag the way you always do. No dictation tool conjures Todoist's parser into existence; it's Todoist's parser doing that work on the text you dropped in. Get the words down fast by voice, let Quick Add sort the metadata.

That same speak-then-clean flow pays off well beyond your task list — you can also type faster with your voice in any app with the one hotkey, so a long description becomes a few spoken sentences instead of a paragraph you thumb out.

When to skip a dictation tool for Todoist

Sometimes the right tool is the one you already have, and pretending otherwise would be dishonest. If you mostly fire quick tasks into Todoist — "pick up dry cleaning," "email the landlord Friday" — Todoist's own voice add is the right call and a dedicated dictation tool is overkill. Open Ramble with Shift+Q, or just say it to Siri. It parses the date, drops the task in, done. For one-line tasks, that's less friction than any external tool, and it's built right in.

Your operating system also covers short bursts for free. On Windows, press Windows key + H and the built-in Voice Typing bar opens wherever your cursor is, a Todoist description included. It punctuates on its own and is fine for short notes. 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. Both type into the focused field, so they reach Todoist's description and comment boxes that Ramble doesn't.

Reach for a dedicated, system-wide tool when the built-ins start hurting: long descriptions, multilingual tasks, offline privacy on Windows, the Ramble session cap getting in your way, or wanting one hotkey that behaves the same in Todoist, your email, and your editor. Below that bar, use what's free — Ramble for tasks, your OS for short text. I'm not going to tell you to install an app to dictate "buy milk."

The same trade-off shows up if you also keep longer notes elsewhere — the logic in dictating into Notion is identical, because there too the cursor, not a built-in voice button, is the real way text reaches every field.

Todoist does have voice now, and it's good at the one thing it does: turning a spoken thought into a task. The moment you want words inside the task — a description, a comment, the actual detail — the cursor is the integration, and a system-wide hotkey fills it. I dictated most of this guide into a text box that wasn't Todoist, with a tool that doesn't care which box it is, then pasted the relevant bits into a task called "ship this article." That's the whole trick.