Voice-first Gemini Live demo: real-time transcription, reasoning and tool calling
AI_Andrew · x · 2026-09-20
Developer AIAndrew built a quick voice-driven app with Google AI Studio and Antigravity, combining Gemini Live with 3.5 Transcribe. The demo does instant live transcription, advanced reasoning and tool calling entirely by voice, inspired by changing autumn leaves. He calls the live transcription "insanely good" while noting the model hedged on whether it's technically still summer. Early exploration, with more to come.
Related event: Developer Builds Open-Source Gemini Live Voice Demo in 20 Minutes(2 posts)→
More from Multimodal
- Experimental video mixes visual styles, generated with Seedance 2.5 on Adobe Firefly — umesh_ai · 2026-11-04
- Hailuo AI claims H3 scored perfect on language tests; Japanese creator praises its Japanese signage fidelity — Hailuo_AI · 2026-11-04
- YANAMI: 400K-dialog multimodal dataset shows models still fail at stateful multiturn interaction — Shengyu Wang · 2026-11-04
- Open-source Idol model turns a single image into 3D in 45s on 8GB VRAM — Promptmethus · 2026-11-04
- ComfyUI v0.44.0 released with new Patina texture nodes — Fcking_Chuck · 2026-11-04
- Krea 3 technical report released: a deep dive into data, architecture and training — bdsqlsz · 2026-11-04