Dictation software for Gmail
Open Gmail. Speak the draft into place.
Open a Gmail Compose or Reply field, speak at the message-body cursor, then correct and send the draft with Gmail.
Downloaded by 150k+ users
Your draft is already open
The message is moving. The keyboard slows it down.
Gmail gives you the thread, the recipients, and the Send button. It does not remove the work of getting a clear thought into the message body.
A new message begins somewhere else
Dictating in a separate app means copying text back into Compose. Your subject, recipients, and next thought are left behind.
A reply loses its thread
A reply only makes sense beside the message you are answering. Leaving Gmail to dictate makes it harder to keep the response on point.
Names pull you back to the keyboard
A client name, team acronym, or product term can turn one correction into several. OpenWhispr gives you a custom dictionary for the words you use.
Speaking is not the last step
A spoken draft still needs a human check. Keep Gmail's recipient, subject, review, and Send controls exactly where they are.
Write the message where it belongs
Compose. Dictate. Review.
OpenWhispr is an input layer for the draft you are already writing. Gmail stays in charge of the thread and the send decision.
Dictate at the active draft
Open a Gmail Compose or Reply field, place the message-body cursor, and speak the first version of the message.
Keep names and terms close
Add recurring names, acronyms, and jargon to your custom dictionary, then review the draft before it reaches a recipient.
Choose Cloud or local
Choose Cloud for top accuracy and speed without a local download, or run local models on-device for offline or sensitive work.
Cloud transcription audio stored
None
Audio is transcribed, then immediately discarded.
To start drafting a Gmail message
$0
Unlimited local AI models are free on every plan.
Custom dictionary
Your terms
Add recurring names, jargon, and acronyms, then review the draft in Gmail.
How it works
From Gmail cursor to reviewed draft
The writing happens in Gmail. OpenWhispr helps you get the first version into the message body.
Download OpenWhispr
Install the free desktop app and choose a Cloud or local transcription option.
Open Compose or Reply
Put the cursor in the Gmail message body and dictate the substance of the email.
Correct, review, and send
Check names, punctuation, recipients, and tone. Send the finished message with Gmail.
Why Gmail writers choose OpenWhispr
10 reasons Gmail writers choose OpenWhispr
A better way to get a thought into the message body, without taking over the inbox.
Start inside Compose
Begin with the cursor in a new Gmail message instead of dictating into a separate document.
Answer the actual thread
Dictate a reply while the original message is still visible, so the response stays tied to the question.
Leave sending to Gmail
OpenWhispr helps create editable text. You inspect recipients and use Gmail's own Send control.
Teach it recurring names
Use the custom dictionary for people, projects, and acronyms that repeatedly need a correction.
Review before it leaves
A spoken first draft gives you text to check for punctuation, tone, and the details that matter in email.
Use Cloud when speed matters
Cloud transcription offers top accuracy and speed with no local model download, then discards the audio immediately.
Use local when the moment calls for it
Local AI models run on your device without internet, useful when you are offline or working with sensitive text.
Choose automatic or manual paste
Automatically paste finished transcription into the active app, or keep dictated text in the clipboard and paste it yourself.
Write across languages
OpenWhispr supports 100+ languages, so a Gmail draft can begin in the language you need to write.
Dictate more Gmail drafts with Cloud transcription
Pro adds unlimited Cloud transcription when the Free plan's 2,000 weekly Cloud words no longer cover your Gmail drafting.
Gmail dictation questions
What to know before you dictate Gmail messages
OpenWhispr helps you draft text. Gmail remains the place where you review recipients and send.
Can I dictate into a Gmail Compose or Reply field?
Does OpenWhispr access my inbox or send messages?
How do I handle names, acronyms, and product terms?
Should I use Cloud or local dictation for email?
Does Cloud keep my email dictation audio?
What do I get for free, and why upgrade?
What users say
Built for people who want more control over their dictation.
From our Discord, GitHub, and inboxes: people who want more control over how they write.
0
Cloud transcription audio retained
In local mode the audio never leaves your device. Nothing is stored on a server, and nothing is sent to a transcriber.
Started using OpenWhispr with my local models and hardware. I have to say, this is better than typing.
I switched to voice input for my Claude Code chats. Even when I stumble and rephrase mid-sentence, the transcription comes out clean and polished.
I needed a local model for when I'm travelling or have no WiFi, and this perfectly solves it. The UI and performance are great.
Pricing
Free forever.
Upgrade when you want more.
FreePopular $0No card details needed | Pro $6.67/user/mo$80/user billed annually Start with Pro | Business $13.33/user/mo$160/user billed annually Start with Business | |
|---|---|---|---|
| Best for | Local Gmail drafting | Frequent Cloud dictation | Teams needing admin and priority support |
| Main reason to choose | Unlimited local models and a custom dictionary | Unlimited Cloud transcription and device sync | Team features, admin, and priority support |
| Offline speech-to-textOffline speech-to-text runs entirely on your own device, it works without internet connection, and it's unlimited and free. | Included | Included | Included |
| Cloud speech-to-textCloud speech-to-text sends audio to OpenWhispr Cloud for the highest accuracy and speed, with no local models to download. | 2,000 words/week via OpenWhispr Cloud, or unlimited using your own API keys | Unlimited OpenWhispr Cloud speech-to-text | Unlimited OpenWhispr Cloud speech-to-text |
| Meeting recordings | 5 hours/month | 20 hours/month | Unlimited |
| Privacy & data handling | Offline audio stays on your device. Cloud audio is sent only to transcribe it, then never stored. | Offline audio stays on your device. Cloud audio is sent only to transcribe it, then never stored. | Offline audio stays on your device. Cloud audio is sent only to transcribe it, then never stored. |
| Setup experience | Hands-on: install app, choose local models, optionally add API keys | Easy: install app, upgrade, use unlimited cloud speech-to-text | Moderate: configure users, Agent mode, and data workflows |
| Advanced features |
|
|
|
| Team management | None | None | Basic team / workflow use |
| Support | Community support | Email support | Priority support |
Need SSO, compliance features, admin controls, or dedicated support for a larger team?
Enterprise adds team features and admin, SSO, SAML, SCIM, audit logs, retention controls, and dedicated support.
Talk to us
Built in the open
OpenWhispr gives Gmail writers an input layer, not a new mailbox.
OpenWhispr is open-source dictation software for getting a spoken Gmail draft into the message body, then reviewing it before it goes anywhere.
Use Cloud when fast, high-accuracy transcription is the priority. Use local models when anyone writing in Gmail needs an on-device or offline option.
And if anything breaks, you talk to the people who built it, in Discord.
Free · open source · local-first
Open Gmail. Speak the draft. Review before you send.
Use OpenWhispr to get the first version into a Compose or Reply field, then keep Gmail's normal review and Send workflow.
Download for freeFree plan available on macOS, Windows, and Linux.