Updates from Hume AI
Building the data and evaluation layer for emotionally intelligent voice AI.
- Hume Audio Decision Benchmarks (Achievement · November 13, 2026)
Hume AI introduced a benchmark for evaluating voice AI systems across text-to-speech, speech-to-speech, and speech understanding, merging objective metrics with human insights. - Introducing Hume's Audio Decision API: A decision layer for speech and sound (Product launch · November 2, 2026)
Hume AI launched an audio-native decision model that allows developers to ask structured questions about speech and sound without requiring transcripts. - Behind Hume’s Expression Measurement Models for Face and Voice (Product launch · October 6, 2026)
Hume AI detailed the development of its expression measurement models, which use over one million human ratings to analyze vocal and facial signals.