Large Audio Language Models
AssessTools
Models that process audio inputs and generate language-based outputs or reasoning.
Why it's here
Placed in Assess: 1 article(s) of evidence from 1 source(s), led by framework updates, with 0 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.
Evidence (1)
- 7Hugging Face Blog·3/24/2026framework_updateHugging Face Blog Introduces EVA for Voice Agent Evaluation
ServiceNow AI researchers present EVA, an end-to-end framework for evaluating conversational voice agents across both task accuracy and spoken interaction quality. The framework outputs two scores, EVA-A and EVA-X, and ships with an airline dataset plus benchmark results for cascade and audio-native systems.