Customer Service Automation
Telexpress wanted to replace rigid IVR workflows with natural, low-latency AI voicebots and chatbots that enterprise customers could adapt to their own routing rules and service processes.
Reported impact
Telexpress improved self-service quality, automated a large share of incoming calls, and reduced the operational burden of running AI customer-service infrastructure.
Telexpress uses Google Cloud to address this challenge: Telexpress wanted to replace rigid IVR workflows with natural, low-latency AI voicebots and chatbots that enterprise customers could adapt to their own routing rules and service processes. Gemini Live API drives the natural voice interactions at the heart of the company’s AI voicebot offering, serving as the serving layer. Gemini 2.5 Flash powers instant, accurate text-based customer service responses for chatbot deployments, serving as the compute layer. Google Kubernetes Engine deploys the AI solutions in autopilot mode so the DevOps team spends less time on infrastructure, serving as the orchestration layer. Customer voice calls enter Gemini Live API, RAG and intent-based routing align each interaction to enterprise workflows, Gemini 2.5 Flash handles text-service channels, and GKE Autopilot runs the platform with less infrastructure overhead.
Customer voice calls enter Gemini Live API, RAG and intent-based routing align each interaction to enterprise workflows, Gemini 2.5 Flash handles text-service channels, and GKE Autopilot runs the platform with less infrastructure overhead.
Gemini 2.5 Flash
Gemini Live API enables around 60% lower latency.
Helps automate 76% of incoming calls, realizing higher customer service quality
Telexpress integrated Gemini Live API into its one-stop customer service SaaS platform.
To reduce infrastructure management workloads, Telexpress uses GKE to deploy its AI solutions.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
11070 臺北市信義區 東興路45號11樓
addressLocality":"Taipei City ","addressRegion":"Taipei ","postalCode":"110","addressCountry":"TW"
Related
Google Cloud Sample Modified · Oct 9, 2026 Tally Group This rapid processing surfaces targeted insights in under 20 seconds, eliminating manual checklists. At utility billing platform Tally Group , call center agents previously navigated up to six applications to… Apigee API Management · BigQuery · Gemini platform Google Cloud Sample Archived · Apr 13, 2026 Trillet Trillet needed to automate complex enterprise calls in sensitive industries, but earlier model choices produced unreliable answers and its fragmented infrastructure made it hard to scale voice workflows predictably and… Achieves <1% error rate Cloud Load Balancing · Gemini · Google Kubernetes Engine Google Cloud Sample Archived · Mar 26, 2026 Cartesia Cartesia needed a globally distributed infrastructure for ultra-low-latency voice AI so developers could deploy realistic speech models and voice agents without sacrificing uptime, data control, or rapid scaling. 40+ languages Cloud Storage · Gemini · Google Kubernetes Engine 