Amazon Connect Voice ID, a feature of Amazon Connect, uses machine learning to provide real-time caller authentication and fraud risk detection to make voice interactions faster and more secure. Historically, contact centers have used a time-consuming knowledge-based authentication process where callers have to answer multiple questions based on personal details, like social security number, date of birth, and mother’s maiden name.

Amazon Connect Voice ID analyzes caller's unique voice characteristic to provide agents and self-service interactive voice response (IVR) systems with a real-time decision on caller's identity for faster and more accurate verification at a very low cost. Amazon Connect Voice ID also screens for fraudulent actors in real-time, based on your contact center’s custom watchlist, reducing potential losses from fraudulent attacks.

Easy customer enrollment and verification

• When a customer agrees to enroll, Voice ID analyzes speech attributes like rhythm, pitch, and tone to create a digital voiceprint, streamlining the authentication experience for customers on their next call. Customers don’t have to say any specific phrases or words, allowing them to maintain the natural flow of conversation.

ML-powered real-time fraud risk detection

• Voice ID analyzes incoming audio and compares them with recordings of known fraudulent actors in your contact center's custom watchlist. During an active call, Voice ID will automatically flag suspicious callers to the agent with a risk threshold (e.g. 'High Risk or 'Low Risk,') — resulting fewer fraudulent attacks on your contact center.

Build a highly efficient and secure IVR

• Add Voice ID to your IVR to deliver secure customer access to self-service requests such as checking refund status or changing contact information. This optimizes agent time and lowers contact center costs.