Gnani.ai partners with Razorpay to enable real-time payment collections via AI voice agents

AI startup Gnani.ai has partnered with fintech firm Razorpay to launch an agentic AI platform that can complete payment collections during live customer calls, the companies said on 26 February, aiming to address a long-standing gap in automated debt recovery.

Traditional voice AI systems can remind customers to pay but typically require them to complete transactions separately, leading to lower conversion rates. The new system allows AI agents to initiate and settle payments within the same conversation, the companies said.

“For the first time, enterprises can automate collections at scale without sacrificing conversion,” said Ganesh Gopalan, founder and chief executive of Gnani.ai. “This integration delivers what voice AI has promised but never achieved: the ability to complete transactions, not just initiate conversations.” 

The platform integrates Gnani.ai’s voice automation technology with Razorpay’s Model Context Protocol (MCP) Server, an AI-native payments layer that enables software agents to initiate, authorise and monitor transactions in real time.

By directly connecting to Razorpay’s infrastructure, the AI can generate payment links or UPI requests, track completion status and confirm settlement without human intervention.

“Agentic AI only becomes truly valuable when it can act, not just converse,” said Khilan Haria, chief product officer at Razorpay. “We’re giving AI systems a secure, real-time pathway to complete payments inside live customer conversations.” 

The companies said the platform currently supports one-time UPI payments and mandate-based recurring payments, with cards and digital wallets planned for future integration.

Gnani.ai said its system processes more than 10 million calls daily and supports over 38 languages, including major Indian languages such as Hindi, Tamil and Bengali, enabling deployment across diverse customer bases.