Anywhere
Types where your caret is
Gmail, Notion, Slack, GitHub, Jira, a search box, a form nobody has updated since 2011. If you can type in it, you can talk into it.
On-device speech recognition · Chrome extension · MIT
Voice dictation that works in any text field on any site — and never sends your audio anywhere. Whisper runs inside your browser on your own hardware. No account, no subscription, no server. Turn off your Wi-Fi and it still works.
Uses your microphone to draw the bars, and nothing else. This page has no server, no analytics and no third-party requests — check your network tab.
The whole story
Most dictation extensions stream your microphone to a company's servers. That means your half-written emails, your client notes and your private messages get transcribed on someone else's computer, under someone else's retention policy. Here is the complete list for this one.
What you get
Dictation you can leave switched on, in the places you already write.
Anywhere
Gmail, Notion, Slack, GitHub, Jira, a search box, a form nobody has updated since 2011. If you can type in it, you can talk into it.
Fast
Runs on your GPU where one is available, drops to WebAssembly where it isn't, and always tells you which is in use.
Quiet
Voice activity detection throws away room tone before it reaches the model — so it costs no compute and invents no words.
Tidy
Fillers removed, sentences capitalised, punctuation spaced. Say "new paragraph" or "question mark" and it does what you mean.
Yours
Add replacements for the names and acronyms Whisper keeps mangling. Ninety-odd languages, or automatic detection.
Open
MIT licensed, no bundler, no minification. The files in the repo are the files your browser runs. Go and check the claims above.
Getting started
The only slow part is the download, and it happens once.
Chrome asks once, for the extension itself. No sign-up, no email.
Base is the right first choice. Tiny if you're on an older laptop, Small if you have a discrete GPU and want the accuracy.
Between 78 MB and 490 MB depending on your choice. It's cached locally and never fetched again.
Talk. The words appear where your caret is. Prefer holding a key? Switch to push-to-talk in settings.
Choose your tradeoff
Decode times are for one eight-second utterance on a 2023 laptop. Yours will differ; the ratios hold.
| Model | Download | WebGPU | CPU | Accuracy |
|---|---|---|---|---|
| TinyShort commands, clean audio, old hardware | 78 MB | ~0.4 s | ~1.6 s | |
| BaseThe sweet spot — start here | 148 MB | ~0.7 s | ~3.4 s | |
| SmallBest accuracy, wants a real GPU | 490 MB | ~1.8 s | ~11 s |
Straight answers
Really offline. After the model download, disconnect entirely and dictate all day. The extension has no backend, so there is nothing for it to phone home to. The one declared host permission is huggingface.co, for the download.
The compute is yours, so there's nothing to bill for. No ads, no data sales, no premium tier. It's MIT-licensed on GitHub and it will stay that way.
Partly, and honestly no extension does better. Docs renders text on a canvas with no editable DOM to type into, so LocalDictate copies your transcript to the clipboard and prompts you to paste. Everything that behaves like a normal text field — including Docs comments — works directly.
It falls back to WebAssembly on the CPU automatically and tells you it has. Tiny and Base remain comfortable; Small will be slow. Check chrome://gpu if you're curious why.
It's Whisper, so: very good in a quiet room with a decent microphone, and noticeably worse with background noise or a heavy accent on the Tiny model. Accuracy is a property of the model, not of this extension — which is also why you can swap models freely.
Only if you want. A local history of the last 100 transcripts is kept in your browser profile so you can recover something you lost. It never leaves your machine, you can export or clear it in one click, and you can switch it off entirely.
Free, open source, and offline the moment the download finishes.