OpenAI · Voice
GPT Realtime 2.1
GPT-Realtime-2.1 updates GPT-Realtime-2 with improved alphanumeric recognition, silence and noise handling, and interruption behavior. It supports speech-to-speech interactions with configurable reasoning effort, instruction following, and tool use for complex voice-agent workflows.
Evidence and sources
Maker HQ: US (according to OpenAI's own website)
Sources: OpenAI API data, AI/ML API data, LiteLLM data, Models.dev data, CometAPI Pricing dataPrimary data from OpenAI API
from AI/ML API: name, primary mode
from LiteLLM: variant, deprecation date
from Models.dev: weights availability
from CometAPI Pricing: description
Input & output
as stated by the model's providersText
Images
Audio
Text
Audio
Also known as: azure/gpt-realtime-2.1, azure/gpt-realtime-2.1-2026-07-07, azure/us/gpt-realtime-2.1, openai/gpt-realtime-2.1
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works