gpt-realtime

Published

Aug 28, 2025

gpt-realtime is an AI model developed by OpenAI (United States), first published in August 2025. It works in the speech, vision and language domain, on tasks such as speech recognition (asr), speech synthesis, visual question answering and 2 more.

Epoch AI has no training-compute estimate for this model.

Access: API access. Its weights are not openly released.

Full record

Organization: OpenAI
Country of organization: United States
Domain: Speech, Vision, Language
Task: Speech recognition (ASR), Speech synthesis, Visual question answering, Speech-to-speech, Audio question answering
Model accessibility: API access
Open weights: No