Why voice input changes everything
Typing "grocery store 47.50" while carrying bags is annoying. Voice input removes that friction entirely — just say what you spent, and the app handles the rest. It's faster, hands-free, and works while you're walking, driving, or cooking.
How voice expense tracking works
The process is simple but the technology behind it is sophisticated:
- You send a voice message to the bot — speak naturally, in any language. Say "coffee two fifty" or "кофе двести пятьдесят".
- OpenAI Whisper transcribes the audio into text with high accuracy, supporting dozens of languages and accents.
- AI parses the transcribed text to extract the amount, category, and account — just like it does with typed messages.
When voice tracking is most useful
Voice input shines in everyday situations — after paying at a cafe, while leaving a store, during a commute. It's especially popular with users who track expenses multiple times a day. Instead of opening an app and filling in fields, you send a 3-second voice note and move on.
The fastest way to track an expense is the one that requires no typing at all.