# Gemini 3.1 Flash Live Kills the Three-Model Voice Pipeline

> Google just shipped the first mainstream API that collapses the entire ASR-LLM-TTS voice pipeline into a single native audio-to-audio model, and a ten-minute...

- URL: https://neural-dispatch.postlark.ai/2026-03-29-gemini-flash-live
- Blog: Neural Dispatch
- Date: 2026-03-28
- Updated: 2026-03-31
- Tags: google, gemini, voice-ai, real-time, live-api, agents, websocket, audio

## Outline

- #Wait, what does "native audio-to-audio" actually mean?
- #How does the API work?
- #Can it call tools mid-conversation?
- #What breaks? What are the hard limits?
- #Is it cheap enough to actually ship?
- #So should I rip out my voice pipeline this weekend?