Gemini Live demoed at Google event, translating English-Japanese sushi order in real time
DynamicWebPaige · x · 2026-09-25
Following Google DeepMind's string of Gemini Audio model launches this week, a well-attended in-person event showcased what the new models can do. Google's developer advocate DynamicWebPaige shared the highlight: she ordered sushi in English with someone who only speaks Japanese, with Gemini Live translating the entire conversation in real time. She says she has been having fun with the new models and can't wait to see what others build.
Related event: Google DeepMind showcases Gemini Audio with live sushi translation demos(5 posts)→
More from Multimodal
- Midjourney SREF pick: --2523103199 for loose pencil-sketch portraits — tisch_eins · 2026-11-11
- Gemini-generated endless loop of quantum cryostats self-assembling — hapticdata · 2026-11-11
- Dad brings his daughter's crayon drawings to life with AI for $1.75, and it's unsettling — Illustrious_Ad_4292 · 2026-11-11
- MOSS-Image-SFT vs MiniMax-H3-Image (Pruned): 1:1 image benchmark across 10 art mediums — SkirtSwimming8950 · 2026-11-11
- UniPath (NeurIPS 2026): adaptively coordinating understanding and generation in one model — jindong_wang92 · 2026-11-11
- An AI-built RPG where a PhD student battles peer reviewers — s_scardapane · 2026-11-11