OpenAI Developers

OpenAI has released gpt-realtime-1.5 in the Realtime API, bringing improvements to voice workflows including more reliable instruction following, tool calling, and multilingual accuracy.

Voice 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 https://t.co/gGV57Wv91V

<p>Voice 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 https://t.co/gGV57Wv91V</p>

TestingCatalog News 🗞

OpenAI has released gpt-realtime-1.5, a new model available through the Realtime API designed for voice agents. The API enables low-latency, speech-to-speech interactions and supports multimodal inputs including audio, images, and text, with outputs in both audio and text formats.

OpenAI released gpt-realtime-1.5 in the Realtime APIs for voice agents. 

"The OpenAI Realtime API enables low-latency communication with models that natively support speech-to-speech interactions as well as multimodal inputs (audio, images, and text) and outputs (audio and text)."

<p>OpenAI released gpt-realtime-1.5 in the Realtime APIs for voice agents. 

&quot;The OpenAI Realtime API enables low-latency communication with models that natively support speech-to-speech interactions as well as multimodal inputs (audio, images, and text) and outputs (audio and text).&quot;</p>

OpenAI released gpt-realtime-1.5 in the Realtime APIs for voice agents. "The OpenAI Realtime API enables low-latency communication with models that natively support speech-to-speech interactions as well as multimodal inputs (audio, images, and text) and outputs (audio and text)."