Voice to text in HubSpot

Does HubSpot have voice to text?

Not for typing. The HubSpot CRM has no built-in dictation or voice-typing feature for writing into a note, an email, or a task by voice. There's no microphone button in the note editor and no voice command for the composer. There's an open idea on HubSpot's own community board asking for exactly this, and at least three separate tools exist that bolt dictation onto HubSpot from the outside — which is the clearest possible signal that the CRM doesn't do it natively. If you've been hunting the editor toolbar for a mic icon, you can stop.

Now, the honest caveat, because this is where people get tangled. HubSpot does have voice features — they're just a different category. HubSpot can record and transcribe sales calls through its call recording and Conversation Intelligence tools. That's a meeting-style feature: it captures a call that already happened and produces a transcript afterward. It is not live dictation. You can't put your cursor in a deal note, talk, and watch your words appear in the field. One records calls; the other types for you while you think. They solve different problems, and conflating them costs an afternoon.

Whisper sits firmly on the dictation side of that line, and I want to be clear about it: Whisper does not join calls, record meetings, or transcribe a Zoom. It is not a meeting bot. It dictates at your cursor. You speak, the words land in whatever field has focus. If you want a transcript of an hour-long sales call, HubSpot's own Conversation Intelligence is the right tool and I'd point you straight at it. If you want to log the recap of that call as a clean note in thirty seconds of talking, that's the gap this guide fills.

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 OS cursor, a HubSpot note is just "any text box." Contact note, deal note, the email composer, a task description — same behaviour in all of them.

That's the part the extension marketplace overcomplicates. There's no HubSpot app to authorize, no OAuth scope to approve, no integration to maintain when HubSpot ships a UI update. Your cursor is in the field, you talk, the words appear in the field. 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. (A HubSpot rep once told me a hotkey "didn't work" — it was clashing with a screen-recording app they ran on every call. 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 already set up dictation on Windows or on Mac, this is the same muscle memory pointed at a different tab.

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 HubSpot open in your 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, logging a call stops being a typing task and starts being a talking task — which, for a salesperson, is the difference between a note that gets written and one that doesn't.

Notes, the email composer, and task descriptions

Because dictation pastes at the cursor, every text field in HubSpot is fair game, and that's the part worth spelling out for a sales workflow. The contact and company note boxes, obviously. The deal note where you log where the deal actually stands. The email composer — dictate the body of a follow-up instead of typing it between calls. Task descriptions, so "call back Thursday re: pricing pushback" gets captured while it's fresh instead of being remembered wrong on Wednesday.

The one that pays off most is the post-call recap. You hang up, your cursor goes in the deal note, you hold the hotkey and just say what happened: who you spoke to, what they pushed back on, what you committed to, when you're following up. Thirty seconds of talking versus three minutes of typing a third of it. The detail that usually evaporates between the call and the keyboard actually makes it into the record. That's the whole pitch — not faster typing, but notes that exist at all.

None of this needs HubSpot to know Whisper exists. It's not an integration, so it doesn't break when HubSpot changes the editor, and it works the same in your Gmail compose box when you're emailing a prospect outside the CRM. One hotkey, every field, whether the field lives in HubSpot or not. For a rep who lives across a dozen tabs, that "same everywhere" property is the actual feature.

Local or cloud: which mode for customer data

For a CRM, think hard about local mode first. The notes you dictate into HubSpot are customer data — names, deal sizes, what a prospect said about a competitor, the reason someone is hesitating. Some of that is the kind of thing your company has rules about. It would be a strange choice to route every spoken call-recap through a third-party cloud to get it into a record you're keeping precisely because it's sensitive. 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 your pipeline runs 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 sell into Chinese, Japanese, or Korean accounts, or need translation, 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 notes most reps put in HubSpot, local is plenty. Both local engines run fully on your machine with nothing sent to a server, which is exactly what you want for customer data. Cloud earns its place when you need top-tier accuracy on a heavy accent or you want the model to pull a fact off the web mid-note. For day-to-day call logging, start local and only reach for cloud when local leaves you wanting.

Turning a spoken call-recap into a clean note

Raw dictation comes out as a run-on. You hang up and say "okay so spoke with maria she's worried about the migration timeline wants a call with our solutions team before she signs follow up friday," 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 rushed post-call dump into something the next rep can actually read — Whisper can run an AI pass. Say the activation phrase "Hey whisper" and the text gets enhanced before it lands in the note. On a local model that runs through Ollama; in cloud mode it's gpt-5-mini by default.

One honest limit, because someone will ask. Dictation gets you clean text into the note field. It does not fill in HubSpot's own structure for you — it won't set the deal stage, associate the note with the right contact, or create the follow-up task as an actual task. You dictate the words; you click the HubSpot controls the way you always do. Anyone promising "say update the deal stage to closed-won and watch it happen" is selling you a demo, not a Tuesday. Get the recap down fast by voice, then use the CRM's own buttons for the CRM's own fields.

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

When to skip a dictation tool for HubSpot

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 HubSpot — a one-line note, a two-word task — 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 HubSpot note 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 — which matters more than usual when the text is customer data. 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 what you actually want is a transcript of the sales call itself, skip dictation entirely — that's HubSpot's own call recording and Conversation Intelligence, built for exactly that job.

Reach for a dedicated, system-wide tool when the built-ins start hurting: long call-recaps, multilingual accounts, offline privacy for customer data on Windows, or wanting one hotkey that behaves the same in a HubSpot note, your email, and your task list. Below that bar, use what's free. I'm not going to tell you to install an app to log a one-line reminder.

The same trade-off shows up if your team also keeps account notes in a separate tool — the logic in dictating into Notion is identical, because there too the cursor, not an integration, is the real connection between your voice and the field.

HubSpot never shipped a microphone button for its note field, and given how much it has invested in call recording instead, I doubt it will rush to. It doesn't need to, because the cursor is the integration. Talk into the field, get clean text, click the CRM's own buttons for the rest. I dictated half of this guide into a text box that wasn't HubSpot, with a tool that doesn't care which box it is, then pasted the lot where it needed to go. That's the whole trick.