Dev builds open-source real-time insurance claim voice agent with Gemini, handles mid-call language switch
Saboo_Shubham_ · x · 2026-09-16
Developer Saboo Shubham demoed an insurance claim agent built on the new Gemini real-time API that can see, talk, think and draw live — and kept working after he switched to Hindi mid-call.
The project is 100% open-source, making it a useful reference implementation for anyone building real-time voice/multimodal agents.
Related event: Dev builds open-source insurance claims voice agent with Gemini Live(2 posts)→
More from Multimodal
- Creator can't stop churning out AI-generated 'slop microdramas' for fun — Kyrannio · 2026-09-16
- StepFun's StepAudio 3 Realtime reasons while speaking, hits 90.6 on MMSU — stepfun-ai · 2026-09-16
- Poolday raises $11M to run full brand-video production from a single prompt — Aiden_Tech_Ai · 2026-09-16
- NoSpoon's microdrama agent is visibly leveling up its dialogue quality — Kyrannio · 2026-09-16
- Seedance turns one image into a 7-shot flooded-forest short with a single prompt — umesh_ai · 2026-09-16
- One image, one prompt, five minutes: AI generates a cinematic short film — umesh_ai · 2026-09-16