build1 publisher
Foundry's voice preview swaps the request/response boundary for a persistent WebSocket session
Microsoft treats speech as its own agent kind, with a managed realtime orchestrator holding the socket open. A dev.to walkthrough sets out why turn detection and tool calls had to be restructured around a few hundred milliseconds.
Publishers:dev.to
Reality
- Evidence38
- Adoption
- Insufficient
- Hype gap+15
- Incentives42
- Confidence40