OpenAI Developers@OpenAIDevsFebruary 23, 2026
Brand new speech-to-speech model from @OpenAIDevs today!
GPT Realtime 1.5 achieves a very nice jump in tool calling and instruction following performance on our voice agent benchmarks.
@charlierguo's demo video shows a great example of perfect performance on a hard end-to-end audio understanding and speech production task: the model captures a seven-character order number (mixed digits and numbers), and repeats it back.
The demo video made me hungry. I definitely need some Inference Chips with my OpenAI Neural Net Burger.
OpenAI Developers@OpenAIDevsVoice workflows just got stronger with gpt-realtime-1.5 in the Realtime API.
The model offers more reliable instruction following, tool calling, and multilingual accuracy.
Demo with @charlierguo
Try GPT Realtime 1.5 for free at https://t.co/3ax0OfzHoN
The open source voice AI LLM benchmark code is here: https://t.co/EPMF7fwVaw
If you're building voice agents, realtime multi-modal AI systems, or are interested in benchmarks, we're talking about all three topics at this month's voice AI meetup on Thursday. Come hang out with us in-person in San Francisco or on the live stream.
RSVP here: https://t.co/SLVzyQQ8wI