ChatGPT leak reveals GPT Bidi 1 voice model that listens and speaks at the same time

Reviewed byNidhi Govil

3 Sources

Share

OpenAI is testing GPT Bidi 1, a new bidirectional audio model that allows ChatGPT to listen and speak simultaneously. The unannounced model has already started rolling out to select ChatGPT app users, suggesting an official release could happen this week. The upgrade promises to transform ChatGPT voice capabilities with natural acknowledgments, better context retention, and seamless interruption handling.

OpenAI Tests GPT Bidi 1 for Enhanced Voice Interactions

OpenAI is quietly rolling out GPT Bidi 1, a new ChatGPT voice model that represents a significant upgrade to the platform's conversational abilities

1

. The unannounced bidirectional audio model has already begun appearing for a select group of ChatGPT app users, with TestingCatalog spotting references to the feature last week and reporting that a wider release could happen this week

1

3

. Internal code describes it as a "major leap in intelligence" and "the next generation of Voice," signaling OpenAI's commitment to making speech the primary way people access AI rather than text

1

.

Source: Analytics Insight

Source: Analytics Insight

Simultaneous Listening and Speaking Changes the Game

The name Bidi is shorthand for bidirectional design, which enables the AI assistant to speak, hear, and listen simultaneously—much like human conversation

1

3

. This bidirectional communication approach marks a departure from traditional voice assistants that require users to wait for responses. The model sits in the ChatGPT voice settings alongside Standard and Advanced options, with the voice bubble turning yellow once GPT Bidi 1 is selected

1

3

. Users can speak naturally while the system responds in real time, eliminating long pauses and creating more fluid speech interface experiences

2

.

Source: Digit

Source: Digit

Natural Voice Conversations With Better Context Retention

GPT Bidi 1 delivers small, natural acknowledgments like "okay" when users pause or slow down, without interrupting the flow of conversation

1

3

. This creates human-like conversations that feel more organic than previous iterations. The model also handles interruptions seamlessly—ask it to count to ten, interrupt to reverse the count, and it adjusts immediately

1

3

. Perhaps most critically, the model maintains conversation context throughout long exchanges rather than dropping earlier information—a weakness that has plagued ChatGPT's current voice stack

1

. The system also avoids jumping in during longer pauses, allowing users to think without being interrupted

1

.

Closing the Gap Between Text and Voice

The release of GPT Bidi 1 represents OpenAI's effort to close the gap between its capable text models and its older voice layer

1

. This matters because the company is betting that speech will become the dominant interface for AI interactions. The timing aligns with OpenAI's broader plans to transform ChatGPT into a superapp, with a major overhaul focusing on the Codex coding tool and agentic AI tools that can perform tasks for users

1

. While OpenAI has not officially announced GPT Bidi 1 or detailed GPT 5.6, the fact that the feature is already appearing automatically for some users suggests a phased rollout is underway

1

3

. Users won't need to subscribe or take additional steps to access the feature once it becomes available

3

. The focus on real-time voice conversations positions ChatGPT to compete more effectively as an everyday AI assistant that understands human behavior and responds naturally

2

3

.

Today's Top Stories

© 2026 TheOutpost.AI All rights reserved