What challenges did EVO Banco face before AI implementation?

Reduce customer call-center workload and improve customer experience by automating telephone-based query handling with natural conversations. Scale call processing and integrate with existing contact-center systems while keeping costs low.

Source

GCPProductionEvidence: Medium65/100

EVO Banco: Developing a human-centric voice banking platform with Google Cloud

Use case typeCustomer service automationUpdated Jun 13, 2026

EVO Banco built a human-centric AI voice banking platform for its telephone contact center so customers could resolve queries through natural conversation rather than a chatbot. The bank uses Google Cloud speech-to-text, Dialogflow, text-to-speech, and Google Kubernetes Engine with PBX/SIP integration, plus machine learning feedback loops to improve routing and effectiveness over time.

Organization: EVO Banco
Industry: Finance
Location: Spain
Published: June 2026

Reported outcomes

Time: 5–6 minutes

Time & speed

Planned next steps

The source says the organization aims to achieve: Enabled natural conversation self-service.

Why do we believe this?Outcome claims, sources, and evidence checks

Normalized claim

Quantified impact: 85%

Google Cloud Customer StoriesJun 6, 2026Customer storyInferred claimMedium evidence strength

Handles around 85% of calls to customer contact centers.

Normalized claim

Time: 5-6 minutes

Google Cloud Customer StoriesJun 6, 2026Customer storyInferred claimMedium evidence strength

Reduces average customer wait time from 5-6 minutes to 2 minutes.

Normalized claim

Time: 95%

Google Cloud Customer StoriesJun 6, 2026Customer storyInferred claimMedium evidence strength

Calls processed through AI are routed accurately 95% of the time.

Normalized claim

Cost: 3%

Google Cloud Customer StoriesJun 6, 2026Customer storyInferred claimMedium evidence strength

Technology costs are 3% of total contact-center running costs.

Normalized claim

Quantified impact: 70% increase

Google Cloud Customer StoriesJun 6, 2026Customer storyInferred claimMedium evidence strength

Conversational effectiveness reaches about 70% with continuous improvement.

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks

Customer: EVO Banco
Provider: GCP
Maturity: Production
Linked source: Google Cloud Customer Stories

Deployed PBX systems inside Google Kubernetes Engine for scalable call processing and real-time demand adaptation

Customer identity supportedSource describes one deploymentMaturity supported

Primary read

Use case focus

Showing 3 of 3

1Contact Center Automation
2Conversational AI
3Voice AI

Transcribed call audio in real time with Cloud Speech-to-Text.
Used Dialogflow to interpret intent and decide whether to answer or route to a human operator.
Used Cloud Text-to-Speech for responses.
Deployed PBX systems inside Google Kubernetes Engine for scalable call processing and real-time demand adaptation.
Applied machine learning to analyzed behaviors and continuously improve system efficiency.

Technologies

Cloud Speech-to-Text Cloud Text-to-Speech Dialogflow Google Kubernetes Engine Asterisk SIP

Architecture

The solution transcribes call audio in real time with Cloud Speech-to-Text, sends text to Dialogflow for intent understanding and response routing, uses Cloud Text-to-Speech for replies, and runs PBX/Asterisk call-processing components in Google Kubernetes Engine with SIP integration for scalable contact-center operations. Machine-learning analysis is used to improve conversational flows over time.

Sources & evidence1

Evidence: Medium65/100Evidence strength