Revolut deployed conversational AI voice agents across the UK and Europe, cutting ticket resolution time by 8x and serving over 4 million customers in 31+ languages — without sacrificing compliance or control.

Serving more than 70 million customers across the globe is no small feat — and doing it well is even harder. As Revolut continues its rapid expansion across markets, the pressure to deliver fast, high-quality support at scale, without inflating costs or compromising on compliance, became a defining operational challenge.
The answer came in the form of conversational AI voice agents.
Revolut's digital-first model had already made its support operations leaner than most. But voice support — the channel customers still reach for when things get complicated — remained difficult to scale. Queues grow. Wait times creep up. Human agents can only handle one call at a time, in one language.
As an engineering-first organization, Revolut's team began with an internal build to test whether AI could fill the gap. The prototypes proved the concept was sound. But turning proof-of-concept into a production-grade system — one that could handle real-time speech processing, live language switching, PCI compliance, and zero-retention data controls — was an entirely different challenge. The infrastructure required to productionize it was a platform-scale undertaking.
That realization led Revolut to evaluate external solutions.
After a rigorous head-to-head evaluation of multiple providers, Revolut selected and deployed an AI voice agent platform to serve as the first line of voice support for customers across the UK and Europe — scaling coverage to more than 4 million customers.
"We tested every major provider. Some lacked flexibility, others missed reliability targets, and a few couldn't match the voice quality necessary where we operate. We needed the best voices and lowest latency, a solution that kept us in control of orchestration, and one that met our security bar with PCI compliance and zero retention options." — Ines Azevedo, Tech Product Owner (AI), Revolut
The deployed agents handle live inbound calls and are built to do three things well:
Crucially, Revolut retained full control of its orchestration layer and business logic. The AI voice platform plugged into Revolut's existing chat and digital AI stack via secure APIs — meaning the company didn't need to rebuild anything it had already built.
"Operating across nearly 40 markets, we needed a provider that could match the complexity, speed, and language support required without making sacrifices on quality. We're very proud of the solution we have built together and are confident that it will continue to scale as we do." — Julia Ponomareva, Director of CX and AI Products, Revolut
The impact was immediate and measurable.
Time to resolution: 8x faster
Call success rate: 99.7%
Languages supported: 31+
AI voice agents now resolve tickets in under 5 minutes on average — a task that previously took 8 times as long when accounting for queue time. With a call success rate above 99.7%, the system operates with a level of consistency that is difficult to achieve at human scale.
These aren't just efficiency numbers. They represent a fundamental shift in what enterprise-grade voice support can look like: premium quality, delivered at a competitive cost, without compromising the compliance controls that a regulated financial institution requires.
"The deployed engineers helped us move fast and accelerate time to value — they were the most responsive partner of all those we evaluated." — Ines Azevedo, Tech Product Owner (AI), Revolut
Revolut isn't stopping at customer support. The company is already exploring new applications for AI voice technology across the broader consumer financial journey — from onboarding to account management to proactive customer engagement.
The goal was simple from the start: give customers a fast, natural conversation with something that can actually help. What Revolut built is a voice channel that meets its bar for cost, compliance, and control — and that creates space for entirely new kinds of customer experience.
At 70 million customers and growing, that kind of infrastructure isn't just an operational upgrade. It's a competitive advantage.