🎙 Hume AI introduces EVI, a voice emotion analysis system
Hume AI has launched the Empathic Voice Interface (EVI) — a speech-to-speech recognition system that analyzes not only the content of words but also the emotional subtext through prosody (rhythm, tone, timbre). The platform is capable of measuring over 48 emotions and 600 vocal descriptors, transmitting them via JSON arrays for application integration.
🌍 The emergence of full-scale APIs for emotional voice analysis paves the way for a new generation of AI agents in HR, medicine, and customer support, where understanding a user's underlying state (stress, burnout, sarcasm) is critical.
👤 Developers can implement "empathy" into their voice interfaces, making them less mechanical and more human-like by using ready-made tools to analyze vocal biomarkers.
Source 1: https://hume.ai/ Source 2: https://dev.hume.ai/docs/speech-to-speech-evi/overview