Say “Minda” and talk. It asks back, works across your apps and answers out loud, and it asks before it pays.
Example: names, numbers and prices are made up
How it works
The shape of light is one of the agent's eleven looks. It takes the form of whatever it is doing, so you can tell at a glance.
01
Say “Minda”, then what you need, the way you would say it to a person. Each stretch of speech, a clip of at most 12 seconds, goes for transcription: to OpenAI with your own key, or to Minda's hosted models on your credits.
02
Short commands, like switching tabs or opening notes, run at once. A job of several steps goes to the SI agent, which plans it and shows the plan as a checklist in the chat.
03
In your signed-in accounts, in tabs of its own: mail, sheets, chats, calendars, shops. Up to three jobs run at once, each reported back when it ends.
04
It answers aloud in the voice and language you chose. Before it pays, places a call or shares a file, it shows the step and waits for your Allow. Talk over it and it stops at once.
A conversation, not commands
Minda asks when it needs to know, stops the moment you talk over it, and checks with you before anything costs money.
Start talking and it stops at once, then takes what you said as the next request. No button, no waiting for it to finish.
MindaThe cheapest is a one-stop at 10:15 for $189, then a nonstop
YouOnly nonstop, please.
MindaGot it, nonstop only. The 7:40 is best, $206 each.
Three steps always wait for your Allow:
PayingPlacing a callSharing a file
PayPay $808 for 2 flights and 3 nights with Visa ending 42?
Allowed · paid and booked
When something is missing, one short question instead of a guess.
YouPlan New Orleans for two in December.
MindaSure. Which dates, and what budget?
YouThe 11th to the 14th, about $1,500.
Say “speak Japanese” and it answers in Japanese from then on. Here is its own reply in each.
わかりました。日本語でお話しします。
Pick how Minda sounds, or say “speak like a kid”.
The mascot's ownA womanA manA kidAn animalOpenAI's natural voicesYour computer's
Hand over a job and keep talking; each tells you when it is done.
Each day's voice conversation is saved as a chat in History, so you can ask about it later, or turn that off.
History · yesterday's voice chat
YouWhat did we decide yesterday?
MindaThursday at three for the launch plan, with Sarah, Ken and Priya, on a video call.
The film
Each plays in the film at the top, with its own place, music and voices. Names, numbers and prices in them are made up.
An example day
Eight things said out loud between breakfast and bed. Minda does the clicking; you do the deciding.
Read me my brief.
Today's meetings and the new notifications, read aloud while the coffee brews.
Send Daniel this month's invoices, in one sheet.
Twelve PDFs read into one Excel sheet with a total, shared on WhatsApp after your Allow.
Summarize this page.
A long report becomes its main points, told to you while you keep reading something else.
Book a table for four near the office at one.
Places nearby checked, one booked, the confirmation in your inbox.
Set up the launch meeting with Sarah, Ken and Priya.
A free hour found, the invite sent with a Meet link, everyone told.
Call Ahmad and talk for me.
It asks first, then talks for you on the call while you listen, and you take over at any moment. Meeting notes keep the call; then it sends him the address.
Plan New Orleans for two, and book it.
Flights, a river-view hotel and dinner, $808, paid only after your Allow.
Play rain sounds, and stop in 30 minutes.
It plays them on YouTube and closes the tab at 23:30.
Say it
One sentence each. Minda works out the steps.
The details
Say “Minda” before a request. Or turn on Listen without “Minda” in the microphone menu: anything that sounds like a request is then acted on. It is off by default.
Each stretch of speech, a 16 kHz clip of at most 12 seconds, is sent for transcription: to OpenAI with your own key, or to Minda's hosted models on your credits. A clip starts only when a human voice is heard. With Keep SI on this computer, Windows' own recognizer hears you instead, in US English.
Before it pays, places a call or shares a file, the step waits in the chat with Allow and Deny. On a WhatsApp, Telegram, Messenger, Instagram or TikTok web call it can talk for you, and you take over whenever you want.
Talk over a reply and it stops at once and takes what you said as the next request. “Stop” ends a command that is taking too long.
The mascot's own voice, a woman, man, kid or animal voice, one of OpenAI's natural voices, or your computer's. English, detect the language, or one of 20 languages.
Each day's voice conversation is a chat in History, searchable and synced like your other chats, unless you turn that off.
Every plan, Free included. Transcription and natural voices use your own OpenAI key, which costs no credits, or Minda SI credits as you use them: Free has 100 a month, Pro 2,000. Your computer's own voice costs nothing.
One of the agent's eleven looks: a swarm of light that takes the shape of each task and stays light on any computer. Pick it in the agent's menu.
Then say what you need. Minda takes it from there, and checks with you before anything costs money.
Agents
Automation
By job
By team
Industries
Guides
Learn
