Hugging Face Blog·· 2026-07-15
Introducing Real World VoiceEQ: Measuring the human quality of voice AI
Introducing Real World VoiceEQ: Measuring the human quality of voice AI
AI summary
Hume released Real World VoiceEQ, a speech evaluation benchmark covering over 40 proprietary and open-source voice models, more than 15 evaluation dimensions and over 60 metrics across ASR, TTS, S2S and speech understanding.
Selection record
Threshold 60Official, first-handFirst 62Second 58
AdmittedSum of both 120 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：发布语音AI人类质量评测基准
- Why it was chosen
- Built from over a million human ratings, the speech benchmark reveals systematic overestimation of real conversational ability by existing metrics.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Hugging Face Blog · huggingface.co