Multimodal model

GPT Realtime 2.1

GPT Realtime 2.1 is OpenAI's realtime speech to speech model, an update to GPT Realtime 2 with improved alphanumeric recognition, better silence and noise handling, and more natural interruption behavior. It supports configurable reasoning effort, stronger instruction following, and reliable tool use for voice agent workflows.

Type
Multimodal
Weights
Closed

Related tools

2

More from OpenAI

14

About OpenAI

1

OpenAI develops and deploys general-purpose artificial intelligence models, products, and developer platforms.

Tools using GPT Realtime 2.1

15