OpenAI

Building with GPT-Live and Image Generation | DevDay 2026

Published 2026-11-11 · Duration 22:38

Summary

This session introduces GPT Live, a full duplex voice model designed for building complex, interactive voice applications. Key architectural concepts covered include full duplex streaming (allowing simultaneous listening and speaking), robust delegation for complex back-end tasks, and a turnless architecture that maintains functionality even with loud background noise. Developers learn how to integrate GPT Live into existing systems using both client and responses delegation modes.

Download summary

Key takeaways

  1. Full Duplex Voice Model

    GPT Live is a full duplex model, meaning it constantly streams audio in and out, allowing it to listen and speak simultaneously. Unlike models reliant on Voice Activity Detection (VAD), it handles turn-taking internally, enabling natural, overlapping conversation flow.

  2. Delegation for Complex Tasks 5:20

    For complex requests (e.g., running a game or fetching data), GPT Live delegates work to a separate back-end agent. This keeps the voice conversation flowing while the backend processes the request, which is crucial for maintaining user engagement.

  3. Turnless Architecture 15:00

    The turnless architecture ensures the application remains functional and responsive even when exposed to loud or noisy background audio (e.g., background music, chatter), greatly expanding use cases beyond quiet environments.

More digests on Voice AI

Technical details

  • GPT Live Architecture 320s

    GPT Live operates with a split architecture (UI, Voice Interface, Backend). Delegation allows the voice model to keep streaming audio while the backend performs work using tools like Astra 6 with code execution.

  • Delegation Methods 450s

    Two primary delegation methods are available: 1) **Client Delegation:** Ideal for existing agent harnesses, where the application receives delegation events and runs the work. 2) **Responses Delegation:** OpenAI manages the delegation process, which is highly familiar to users of tool calling and structured outputs.

  • Information Streaming 380s

    The backend can provide three types of information to the voice model to maintain context and steer the conversation: 1) **Silent Context Updates:** Keeps the model informed of background state. 2) **Speakable Content:** Passes data through the commentary stream for the model to announce aloud. 3) **Instructions Stream:** Used to change model behavior (e.g., guardrails or system instructions).

Mentioned resources

  • OpenAI Developer plugin (Plugin/Tool)
  • GPT Live Starter app (Application)

Channel & topics

Watch on YouTube · Back to latest

This independent, AI-assisted summary is provided for commentary and informational purposes. It may contain errors or omit important context. Please watch the original video for the creator's complete presentation. Video, thumbnail, and related copyrights belong to their respective owners.