Voice Expense Tracker for iPhone, Just Say It | Cash Book
Quick answer
Voice logging in Cash Book is one tap and one sentence. You press the coral mic at the bottom of the Home screen and say what you spent, in your own words and in any major language. An AI model turns the audio into one or several transactions, each with an amount, a merchant or note, a tag and a date. They appear on Home with an Edit option, so a wrong tag or a misheard number is a two-second fix. It needs a connection, and the audio is not kept after the response.
Most expense trackers fail for one reason: logging takes long enough that you stop doing it. Cash Book exists to fix that, and the mic is where it starts.
Talk like you'd tell a friend
Tap the coral mic circle at the bottom of Home and say what you spent. There is no form to fill and no menu to pick from first. "Twelve euros lunch at Beshamel" is a complete entry. So is a run-through of the whole day on the walk home: "coffee three fifty, groceries forty-two at Lidl, twenty on petrol, and I got paid the fifty back from Ana".
Cash Book sends the audio to an AI model, which returns one transaction per thing you mentioned. Each one carries an amount, a merchant or note, a tag and a date. If you said "yesterday", the date moves. If you said "Ana paid me back", it lands as income rather than an expense.
What the AI fills in
The parts you would normally tap through are inferred instead. The amount comes from what you said, in whatever currency you speak in. The merchant becomes the note. The tag is matched against your own tags, so "groceries" goes to your Groceries tag with its emoji squircle, and the AI prefers one of your existing tags over inventing a new one. Everything that is not obvious falls back to a sensible default you can change.
This works in any major language, and the merchant names can be in another language again. Someone logging in Spanish with a German shop name gets the same result as someone logging in English.
Review before it sticks
Nothing is written silently. After a voice log, the new transactions appear on Home in the day's list with an Edit option right there. Open one and you get the same sheet the keypad uses: amount, tag chips, note, date, account and the Expense, Income or Transfer pill. A misheard number is a two-second fix, and the AI learns nothing about you it needs to keep, because the audio is processed and dropped.
Voice logging needs a connection, since the parsing happens through the app's relay. Offline, the keypad is always one tap away, and the camera is there for the moments when the receipt is easier to show than to describe.
When it earns its keep
The point of voice is not novelty. It is that the log gets done in the moment, while you still remember what the twelve euros were for. That matters more than any chart, because the insights and budgets are only as honest as the entries underneath them.
If you want the full walk-through, from the first tap to fixing a tag, read how to log expenses by voice. It takes about as long to read as it takes to log a week.
Frequently asked questions
What can I say?
Anything that sounds like a purchase. “Twelve euros lunch at Beshamel” is enough for one entry. “Coffee three fifty, groceries forty-two at Lidl and the gym fee” gives you three. Amounts, merchant names, tag hints and days like “yesterday” are all picked up.
Does it work in my language?
Yes. Voice logging understands spoken expenses in any major language, and you can mix in merchant names in another language without breaking it. The interface itself ships in 26 languages.
Is my voice recording stored?
No. The clip goes through the studio's relay to an AI model for parsing, and nothing is kept after the transactions come back. Usage analytics only count that a voice log happened, never what was said.
What if the AI gets something wrong?
Every voice log shows the result with an Edit option. Change the amount, tag, account or date in the same sheet the keypad uses. Nothing is saved behind your back.
Get Cash Book on the App StoreFree for 7 days. $19.99 once for lifetime.