"Voice AI" is really Text AI with a voice overlay

Language Log 2026-06-26

Summary:

Martijn Bartelds, Federico Bianchi, James Zou, "Real-Time Voice AI Hears but Does Not Listen", 6/24/2026: Speech conveys information through both words and vocal delivery. We evaluate four leading production realtime voice systems – OpenAI's GPT Realtime 2, Google's Gemini 3.1 Flash Live, and Alibaba's Qwen3.5 Omni Plus and Omni Flash – on tasks where the […]

Link:

https://languagelog.ldc.upenn.edu/nll/?p=73756&utm_source=rss&utm_medium=rss&utm_campaign=voice-ai-is-really-text-ai-with-a-voice-overlay

From feeds:

Gudgeon and gist » Language Log

Tags:

artificial

Authors:

Mark Liberman

Date tagged:

06/26/2026, 23:15

Date published:

06/26/2026, 20:36