February 27, 2024

With the addition of a voice-based operate, India’s UPI cost system is able to bear a metamorphosis. This invention makes an attempt to earn a living transfers simpler by permitting customers to begin transactions utilizing voice directions moderately than text-based enter.

RBI Governor Shaktikant Das introduced the plan to introduce this voice-based UPI cash switch know-how at a latest international fintech occasion in Mumbai.

This new operate is meant to be a sport changer, particularly for seniors and anybody with minimal digital literacy or smartphone utilization expertise. It can additionally attraction to people who find themselves extra comfy talking regional languages than English.

Utilizing UPI With Voice Instructions

The UPI cost functionality based mostly on voice will probably be built-in into UPI functions, telecom calls, and Hindi and English IoT units. Different regional languages will probably be added to the system within the close to future.

Customers simply ship a voice command and enter their UPI PIN to execute a speech-based UPI transaction. NPCI has created cost fashions in Hindi and English at the side of IIT Madras’ A14 Bharat Bhashini Program.

Growing Demand For Voice Searches

Voice search demand has been regularly rising, with a staggering yearly rise of 270%. The UPI voice-based switch system will probably be out there in two modes: on-call and in-app. 


To complete the cost process, customers will contact a sure quantity and comply with the IVR (Interactive Voice Response) directions.


Voice enter is out there throughout the UPI utility, the place the system detects and responds to voice directions.

How Does The System Work?

A number of steps are concerned within the course of:

  • Human speech is digitally remodeled.
  • Speech recognition acknowledges and turns voice enter into textual content.
  • Pure Language Processing (NLP) converts speech enter into the required language, which is often English.
  • The system acknowledges the person’s function and processes the voice command appropriately.
  • The system creates a voice output, which the person hears, verifies, and conducts the transaction.