Dictation app for ChatGPT

Hold the hotkey. Get a prompt you can edit.

On desktop, OpenWhispr turns speech into editable text at a focused writable cursor. With a ChatGPT prompt field focused, review the prompt before you send it.

Downloaded by 150k+ users

Woman in a mustard jacket talking on a garden bench with a laptop and notebook on her lap.
Use at the active cursor:
ChatGPTMicrosoft WordGmailNotionSlackObsidian

The prompt-writing moment

You know the context. Typing it all is the slow part.

A useful prompt needs the details in your head, but you still want to read it before ChatGPT gets it.

The prompt needs more than one neat sentence.

Goals, background, constraints, and the format you want are easy to leave out when every extra detail means more typing.

A spoken thought is not ready to send.

You need editable text in the prompt field, where you can cut repetition, add exact terms, and decide what ChatGPT should see.

A transcript in another window creates another task.

Copying, finding the prompt again, and moving text across windows breaks the thought before you have even reviewed it.

A ChatGPT integration is not what this is.

OpenWhispr uses system-wide desktop dictation at the active cursor. It does not install inside ChatGPT or send prompts for you.

Dictation for the prompt in front of you

Say the context. Shape the prompt before it goes anywhere.

Use a global hotkey while the ChatGPT prompt field is focused. Local transcription is unlimited on every plan.

Smiling man in a denim shirt holding a tablet in a leather armchair.

A hotkey, then editable text in the prompt field

Focus the ChatGPT prompt field on desktop, hold your OpenWhispr hotkey, and speak. The app uses the focused writable cursor for its paste path.

Woman in a green sweater holding a pen and notebook beside an open laptop.

Choose the processing route that fits the prompt

Local models run on your device and work offline. OpenWhispr Cloud offers top accuracy and speed without a local model download, then immediately discards transcription audio.

Man typing on a laptop at an outdoor café table by the sea.

Keep the parts that must be exact

Dictate the explanation, then use the keyboard for exact code, names, links, or quoted text before sending the prompt.

Cloud transcription audio retained

None

Cloud audio is transcribed then immediately discarded. Local audio stays on your device.

Cost for local desktop dictation

$0

local dictation is unlimited on every plan, including Free

Desktop start

Hotkey

download, choose a model, focus a writable prompt field

From desktop hotkey to prompt

Focus the prompt. Speak the context. Review the request.

OpenWhispr uses system-wide desktop dictation. It does not install inside ChatGPT or claim a native connection.

Woman in a blue shirt talking toward a laptop on her lap on a sofa.

Download for free.

Install on macOS, Windows, or Linux. Local models are unlimited on every plan and can run offline.

Focus ChatGPT, then hold the hotkey.

Keep a writable ChatGPT prompt field focused in your desktop browser. Speak the context and OpenWhispr uses its paste path for that active cursor.

Review the editable prompt.

Correct the request where you are already working, then send it when it says what you mean. If automatic paste is unavailable, paste copied text manually from the clipboard.

The desktop route, clearly bounded

10 reasons ChatGPT users choose OpenWhispr

For people who want speech to become editable text in the active desktop prompt field, without claiming a ChatGPT integration.

The prompt field stays the destination.

OpenWhispr is built to paste dictated text at a focused editable cursor. With a ChatGPT prompt field focused, that is where you review the request.

No ChatGPT add-on to install.

The workflow relies on the desktop app's system-wide hotkey and paste behavior, not a ChatGPT extension, plugin, sidebar, or native integration.

Speak the detail that typing leaves out.

Use the hotkey to capture the background, constraints, audience, and output format that make a ChatGPT prompt specific enough to review.

See which details you have already said.

With local transcription, turn on Live Transcription Preview to read a floating transcript as you speak. Check which constraints you have covered before finishing a long prompt.

The keyboard still handles exact fragments.

Use speech for the explanation, then add exact code, commands, names, numbers, or quoted text with the keyboard before sending.

Local works when the connection does not.

Choose local models for on-device, offline transcription. You can keep composing the prompt on your desktop even without an internet connection.

Local desktop dictation is unlimited and free.

Every plan includes unlimited local AI models. The Free plan's 2,000-word weekly limit is for OpenWhispr Cloud transcription, not local dictation.

Cloud is the no-download route.

OpenWhispr Cloud is the choice for top accuracy and speed without downloading local models. Cloud transcription audio is immediately discarded.

A custom dictionary can help with prompt terms.

Add recurring names, jargon, and acronyms to OpenWhispr's custom dictionary for sharper transcripts when your prompt uses specialized language.

Pro adds cloud and cross-device workflow features.

Pro includes unlimited OpenWhispr Cloud transcription, sync across devices, personal API access, MCP integration, and the iPhone and iPad app. None of those features claim a native ChatGPT integration.

Before you choose a route

Questions about dictating ChatGPT prompts.

Straight answers on desktop, editable text, privacy, cost, and the integration boundary.

What people tell us

A desktop app for prompts you can inspect.

These are general product reviews, not claims of a native ChatGPT integration.

Editable

Text before sending

The relevant product behavior here is system-wide desktop dictation with paste at a focused editable cursor, plus a clipboard fallback.

Started using OpenWhispr with my local models and hardware. I have to say, this is better than typing.
0xSero@0xSero
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.
j3iiifn@j3iiifn
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.
Gabe@gabe__perez

Pricing

Free forever.
Upgrade when you want more.

Compare plans for desktop ChatGPT prompts. Other included features are listed for work beyond this workflow.
Free
$0No card details needed
Pro
$6.67/user/mo$80/user billed annually
Start with Pro
BusinessMost Popular
$13.33/user/mo$160/user billed annually
Start with Business
Best forChatGPT users trying spoken prompts with local models or the Free Cloud allowanceFrequent ChatGPT prompt writers who want unlimited Cloud transcriptionPrompt writers who also want priority support and tools for work beyond ChatGPT
Main reason to chooseUnlimited local prompt dictation plus 2,000 OpenWhispr Cloud words each weekDictate prompts with unlimited OpenWhispr Cloud transcription and no local model downloadPro's unlimited Cloud dictation plus priority support; extra recording and data tools for other work
Offline speech-to-textIncludedIncludedIncluded
Cloud speech-to-text2,000 words/week via OpenWhispr Cloud, or unlimited using your own API keysUnlimited OpenWhispr Cloud speech-to-textUnlimited OpenWhispr Cloud speech-to-text
Meeting recordings5 hours/month20 hours/monthUnlimited
Privacy & data handlingOffline 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 experienceHands-on: install app, choose local models, optionally add API keysEasy: install app, upgrade, use unlimited cloud speech-to-textMore: unlimited meeting recordings and chat over your data
Advanced features
  • Custom dictionary improves names/terms
  • 100+ languages multilingual speech-to-text
  • Custom dictionary improves names/terms
  • 100+ languages multilingual speech-to-text
  • Device sync use across devices
  • Mobile companion app dictate on mobile
  • API / MCP access connect tools/workflows
  • Agent mode automate actions
  • Custom dictionary improves names/terms
  • 100+ languages multilingual speech-to-text
  • Device sync use across devices
  • Mobile companion app dictate on mobile
  • API / MCP access connect tools/workflows
  • Agent mode automate actions
  • Chat over your data ask about files/transcripts
Team managementNoneNoneBasic team / workflow use
SupportCommunity supportEmail supportPriority support

Need SSO, compliance features, admin controls, or dedicated support for a larger team?

Contact us about Enterprise.

Talk to us
One of OpenWhispr's founders

Why we built it

The prompt belongs where you are ready to send it.

OpenWhispr started with a simple objection: getting your own words into a prompt faster should not mean moving a transcript between apps.

On desktop, its system-wide hotkey uses a focused editable cursor. That is useful in ChatGPT without being a ChatGPT add-on.

And if anything breaks, you talk to the people who built it, in Discord.

Free · open source · local-first

Open ChatGPT. Press the hotkey. Shape the prompt.

Download OpenWhispr for desktop and turn speech into editable text at a focused cursor. It is system-wide dictation, not a ChatGPT add-on.

Download for free

Free to download on Mac, Windows and Linux.