Amplify launches AI–powered custom speech recognition promising to support next-generation voice-enabled learning
Amplify, a curriculum and assessment publisher, has announced the launch of a custom Automatic Speech Recognition (ASR) system designed to support voice-enabled speech education products.
Amplify’s ASR system converts spoken language into written text, allowing users to interact with educational software using voice commands, while giving detailed feedback on pronunciation, prosody and more.
The technology is said to support multiple applications including reading assessments, conversational tutoring, digital activity input, and classroom monitoring. It will also compare student speech to target texts and identify areas for additional support.
"Voice interaction is becoming increasingly important for young students using educational software, and we're seeing tremendous potential for growth in this area," says Alexandra Walsh, Chief Product Officer at Amplify. "By developing our own ASR solution, we can test, refine, and deliver voice-enabled features that directly support student learning outcomes while meeting our high standards for safety, accountability, fairness, and efficacy."
Amplify ASR will support voice-interactive instructional programs for the 2025-2026 school year across four key areas:
reading assessment and practice, focusing on phonics, automaticity, and prosody
conversational tutoring systems
voice input for digital activities and assessments
classroom monitoring tools that provide teacher feedback and student insights
Amplify says the application will initially replace Soapbox’s ASR functionality in its mCLASS Literacy and Boost Reading programs with plans for organization-wide expansion.
Earlier this year, Amplify’s mCLASS system was approved by the California Reading Difficulties Risk Screener Selection Panel as one of only three recommended tools for identifying reading difficulties in K–2 students.
