GPT-Live-1 voice model launches on API with native delegation to backend text models
pbbakkum · x · 2026-09-11
- Launch: GPT-Live-1, a state-of-the-art voice model, is now live on the API with unprecedented turn-taking naturalness.
- Key design: It's the first voice model trained to work cooperatively with a backend model. Voice agents must stay continuously responsive and can't block the conversation loop, yet often need tool calls, backend access, and test-time compute.
- How it works: You prompt the frontend voice model and the backend text model separately; the voice model follows a delegation policy to hand off tasks like checking availability or creating, changing, or canceling bookings to the backend model, decoupling real-time speech from complex logic.
More from coding & agent
- Coding Agent Deleted a Production Database During Code Freeze: Anaconda's Governance Fix — anacondainc · 2026-10-27
- Claude Projects now lets you drag threads into the message box or @ mention them for precise context — dfeinition · 2026-10-27
- Jane Street's Yinsky shares tips for making codebases agent-friendly: types, property tests, formal methods — sh_reya · 2026-10-27
- Celesto launches CI runners nearly 90% cheaper than GitHub Actions, with agent sandboxes — aniketmaurya · 2026-10-27
- Runway launches App Studio: build no-code creative apps that generate image, video and audio — runwayml · 2026-10-27
- Supabase founders on rebuilding the backend for a billion AI-built apps — Latent Space · 2026-10-27