# OpenAI releases GPT-Live-1.1 voice model with full-duplex support

Digest AI · Generative AI & Models · published 2026-10-16T01:15:00Z

Canonical: https://digestai.news/story/openai-releases-gpt-live-1-1-voice-model-with-full-duplex-support

## Summary

OpenAI launched **GPT-Live-1.1** and **GPT-Live-1.1 Quip** on October 15, 2026, marking the next iteration of its voice AI models. The key innovation is full-duplex capability, enabling simultaneous listening and responding to mimic natural human conversation—handling pauses, interruptions, and varying speech rhythms. This replaces the previous **GPT-Live-1 mini** and will serve as the default voice model for **Plus subscribers and above**, as well as in **Codex** and **Dots**, signaling a push toward voice-driven AI agents.

The system card highlights a **two-model architecture**: GPT-Live handles voice interaction while delegating complex tasks to a backend model (e.g., **GPT-5.6 Terra**), inheriting its safeguards. OpenAI’s safety evaluations show **no statistically significant regression** in production prompts but reveal **declines in four risk categories**—sexual content, mental health, emotional dependency, and gore—based on synthetic tests. The company notes these are edge cases and plans further research. Alignment tests also show minor variations in adherence to restrictions and deception resistance, though all GPT-Live models outperformed the base model. OpenAI advises deploying voice AI with system-level safeguards, not just model-based ones, and emphasizes separating voice UI design from task delegation.

## Key points

- GPT-Live-1.1 adds full-duplex voice, responding mid-conversation to match human rhythms
- Default for OpenAI Plus+ users and integrated into Codex and Dots as of October 15, 2026
- Safety tests show no regression in real-world prompts but four risk areas worsened in synthetic tests

## Why it matters

Full-duplex voice AI could redefine hands-free interactions for agents, but OpenAI’s mixed safety results highlight trade-offs in naturalness versus risk. The delegated architecture may ease adoption for businesses testing voice-first workflows.

## Sources

1. [OpenAI's "GPT-Live-1.1" Arrives! Decoding the Capabilities and Safety Evaluations of Full-Duplex Voice AI](https://note.com/fastest_purple/n/n88dad00641c6?hl=en) (note.com, 2026-10-16)

## Cite

Digest AI, "OpenAI releases GPT-Live-1.1 voice model with full-duplex support", 16 October 2026, https://digestai.news/story/openai-releases-gpt-live-1-1-voice-model-with-full-duplex-support

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/openai-releases-gpt-live-1-1-voice-model-with-full-duplex-support.json