top of page

Voice based transaction system

Updated: Mar 13

The introduction of AI in digital payments through the Unified Payments Interface (UPI) in India is aimed at making transactions more convenient and intuitive. With "Conversational Payments," payment requests can be seamlessly integrated into chat or message conversations, allowing for quick and efficient money transfers during daily interactions. This innovative feature could potentially simplify the payment process and enhance the overall user experience.

In 2016, PayPal became one of the first significant payment services to introduce voice-activated technology for processing transactions. Through integration with Apple's Siri, PayPal enabled users to conduct peer-to-peer transactions simply by using voice commands on their iPhone devices. This innovation allowed for a more seamless and convenient payment experience for PayPal users.

PayPal’s Meron Colbeci said consumers in 30 countries would be able to use the new service. Now how can we Integrate this in India’s payment system. voice-activated payment processing is still an emerging technology in India, but there are some initiatives and developments that are paving the way for its adoption. For instance:


UPI Lite: UPI Lite is a lighter version of UPI, designed for small-value transactions. UPI Lite allows users to make payments without using a PIN up to Rs. 500 per transaction, and supports offline transactions using Near Field Communication (NFC) technology. UPI Lite can be used for contactless payments in situations where internet or telecom connectivity is weak or unavailable. Voice commands can be used with this, since the security process is minimal and there already exists the required technologies already.

Google Pay: Google Pay is a popular UPI app that allows users to make payments using voice commands through Google Assistant. Users can link their Google Pay account to their Google Assistant and say commands like “Ok Google, send Rs. 100 to Rajesh on Google Pay” or “Ok Google, request Rs. 200 from Priya on Google Pay” to initiate transactions.

Amazon Pay: Amazon Pay is another UPI app that enables users to make payments using voice commands through Alexa. Users can link their Amazon Pay account to their Alexa and say commands like “Alexa, pay Rs. 500 to Ravi on Amazon Pay” or “Alexa, ask Amazon Pay to send me Rs. 300” to initiate transactions

Technological requirements for incorporating voice based transactions:

Voice pay utilizes natural language processing to learn, understand, respond, and produce content in human languages. This technology works closely with voice recognition engines. For example, voice assistants such as Amazon’s Alexa or Apple’s Siri utilize AI-enhanced voice recognition technology, where human speech is converted from analog to digital form. The machine then receives, interprets, understands, and performs the spoken commands. As a result, NLP is a crucial component in making voice payments possible, Indian accent speech recognition. Traditional ASR (Signal Analysis, MFCC, DTW, HMM & Language Modelling) and DNNs (Custom Models & Baidu DeepSpeech Model) on Indian Accent Speech platform to integrate UPI with voice commands.

The challenges in ASR include

  • Variability of volume

  • Variability of words speed

  • Variability of Speaker

  • Variability of pitch

  • Word boundaries: we speak words without pause.

  • Noises like background sound, audience talks


There are also some challenges and limitations that need to be addressed, such as:

  1. Many users may not be aware of the availability and benefits of voice-activated payment processing, or may not trust the technology enough to use it. Therefore, there is a need for more education and awareness campaigns, as well as incentives and rewards, to encourage users to try and adopt voice-activated payment processing.

  2. Regulatory and compliance issues: Voice-activated payment processing involves sensitive personal and financial data, which may raise concerns about privacy, security, and fraud. Therefore, there is a need for clear and consistent regulations and guidelines, as well as robust security and authentication measures, to ensure the safety and integrity of voice-activated payment processing.

  3. Technical and infrastructural challenges: Voice-activated payment processing requires reliable and high-quality voice recognition software, as well as adequate internet and telecom connectivity, to function effectively. Therefore, there is a need for continuous research and development, as well as investment and innovation, to improve the technical and infrastructural aspects of voice-activated payment processing.

5 views0 comments


bottom of page