Full-duplex voice model removes turn detection, lets you interrupt mid-response; client delegation routes complex work to any text model while voice continues.
Summary
Eliminates latency gaps in voice interactions by supporting simultaneous listen/speak. Delegation model control stays in your application—you gate what secondary models can do, how they're billed, and when they run.
Why it matters
Eliminates latency gaps in voice interactions by supporting simultaneous listen/speak. Delegation model control stays in your application—you gate what secondary models can do, how they're billed, and when they run.
Implementation verdict
Replaces synchronous turn-based voice flows. Requires AI SDK 7, @ai-sdk/openai 4.0.67+, WebSocket client, and AI Gateway API key. Ready now—code examples provided, docs link included. Start with non-delegation flow to validate audio pipeline.
Sources
Dev Signal
Get briefs like this in your inbox — free, every weekday.
100+ sources compressed into one 4-minute read. Ranked, cited, implementation-ready.